© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93402
    Prev
    Next
    INDEX
    Explanations

    . Paper citations

    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
     this
    -1.31
     their
    -1.23
     of
    -1.23
     different
    -1.22
     all
    -1.13
     relatively
    -1.12
     using
    -1.11
     mostly
    -1.09
     that
    -1.08
     even
    -1.05
    POSITIVE LOGITS
    warz
    1.14
    donde
    1.09
    ⅖
    1.01
    ⅗
    1.00
    ולים
    0.99
     hebt
    0.99
    
    0.98
    や
    0.98
    ཥ
    0.97
    彷
    0.96
    Activations Density 0.014%

    No Known Activations