© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 66926
    Prev
    Next
    INDEX
    Explanations

    controlled by

    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
     {
    
    
    -1.63
    するもの
    -1.39
    These
    -1.38
    what
    -1.36
    ⠗
    -1.33
    стреча
    -1.31
    𝒟
    -1.30
    Those
    -1.29
     relâche
    -1.27
    Recently
    -1.27
    POSITIVE LOGITS
     and
    2.30
     of
    2.27
     that
    1.86
     also
    1.80
     on
    1.59
     other
    1.51
     at
    1.50
     from
    1.48
     with
    1.43
    breviations
    1.42
    Activations Density 0.070%

    No Known Activations