© 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. 22-GEMMASCOPE-RES-131K
    4. 12795
    Prev
    Next
    INDEX
    Explanations

    events and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    大丈夫です
    -1.32
    ふん
    -1.18
    ことが
    -1.17
     organismes
    -1.17
     Provides
    -1.15
     новом
    -1.13
     после
    -1.12
     Klagen
    -1.12
    也想
    -1.11
    と共に
    -1.09
    POSITIVE LOGITS
    2
    1.31
    0
    1.20
    1
    1.14
     Besonder
    1.11
    losen
    1.10
    ındaki
    1.09
    Referenties
    1.06
     what
    1.05
    <bos>
    1.04
     to
    1.04
    Activations Density 0.018%

    No Known Activations