© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 111145
    Prev
    Next
    INDEX
    Explanations

    forensic analysis of evidence

    np_acts-logits-general · gemini-2.5-flash-lite

    terminology and concepts related to forensic analysis and investigation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    technical or scientific terms related to forensic investigation, evidence collection, and DNA analysis.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    дву
    -1.31
     eléctrica
    -1.28
    daß
    -1.23
    xxxxxxxxxxxxxxxx
    -1.20
    ditto
    -1.19
     можно
    -1.17
    seperti
    -1.16
    thiết
    -1.16
    infor
    -1.16
    💟
    -1.15
    POSITIVE LOGITS
    七月
    1.50
    </strong>
    1.42
    ismet
    1.27
     після
    1.27
    cett
    1.24
    ratu
    1.22
     cauza
    1.21
    ganu
    1.20
    after
    1.19
    kami
    1.18
    Activations Density 0.046%

    No Known Activations