© 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. 87261
    Prev
    Next
    INDEX
    Explanations

    method definition

    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
    起きた
    -1.56
    この日
    -1.47
    台風
    -1.41
     melap
    -1.36
     also
    -1.36
    UITextField
    -1.34
    久しぶりの
    -1.33
     mengucap
    -1.32
    暑い
    -1.31
    気持ちが
    -1.31
    POSITIVE LOGITS
    -
    1.55
    v
    1.48
     lesquels
    1.46
     lesquelles
    1.43
    ds
    1.39
    </em>
    1.38
    d
    1.34
    1.33
    tes
    1.31
    g
    1.31
    Activations Density 0.020%
    No Known Activations