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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 103010
    Prev
    Next
    INDEX
    Explanations

    query by prefix

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

    compound technical terms or product names, particularly software/technology-related proper nouns (like "BigQuery", "Intune", "PARAFAC", "HANA").

    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
     it
    -1.58
     It
    -1.44
    lindo
    -1.25
    6
    -1.24
    lindungi
    -1.20
     Of
    -1.18
    hydrat
    -1.14
     hatten
    -1.13
    ковь
    -1.13
    enada
    -1.13
    POSITIVE LOGITS
    。”
    1.84
    ”。
    1.60
    ”,
    1.60
    。」
    1.59
    !”
    1.58
    ).”
    1.58
     maksi
    1.55
    )."
    1.54
    </em>
    1.53
    isieren
    1.50
    Activations Density 0.120%

    No Known Activations