© 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. 10-GEMMASCOPE-RES-131K
    7. 75330
    Prev
    Next
    INDEX
    Explanations

    irreversible damage

    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_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
    {
    -4.97
    に
    -2.91
    er
    -2.89
    ان
    -2.89
    0
    -2.72
    an
    -2.69
    но
    -2.52
    self
    -2.48
    [
    -2.44
    .
    -2.33
    POSITIVE LOGITS
    𝄆
    2.80
    ,:);
    2.53
    ſſi
    2.48
    炱
    2.44
    韭菜
    2.41
    檍
    2.36
    ruecos
    2.34
     \%$
    2.28
     entrust
    2.25
    这一切
    2.23
    Activations Density 0.014%

    No Known Activations