© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15768
    Prev
    Next
    INDEX
    Explanations

    hexadecimal numbers

    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
    <bos>
    -1.70
    がありますが
    -1.52
    それにしても
    -1.44
     onPostExecute
    -1.42
    など
    -1.41
    などの
    -1.36
    tembro
    -1.33
    と
    -1.33
    冒険
    -1.33
    与此同时
    -1.31
    POSITIVE LOGITS
    為に
    1.52
     guapos
    1.38
    のではなく
    1.34
    ためには
    1.34
    際には
    1.34
     aanzien
    1.28
    無論
    1.28
    のでは
    1.26
    imanapun
    1.26
    ようです
    1.24
    Activations Density 0.008%

    No Known Activations