© 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. 54422
    Prev
    Next
    INDEX
    Explanations

    bin/ paths and commands

    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
    椟
    -2.70
    呖
    -2.70
    CHREIB
    -2.33
    胪
    -2.28
    $};
    -2.27
    ेमाल
    -2.25
     Houſe
    -2.25
    </h6>
    -2.25
    },
    -2.22
    ᐕ
    -2.22
    POSITIVE LOGITS
    {
    3.14
    2
    3.05
    That
    2.86
    \
    2.78
    During
    2.72
    From
    2.66
    At
    2.66
    With
    2.61
    After
    2.56
    All
    2.50
    Activations Density 0.010%

    No Known Activations