© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74170
    Prev
    Next
    INDEX
    Explanations

    code elements and identifiers

    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
    ༀ
    -1.40
    ḏ
    -1.31
     Mě
    -1.31
    krok
    -1.27
     pels
    -1.27
     scoperto
    -1.27
    ковая
    -1.27
     our
    -1.25
    ᐕ
    -1.24
    ⬎
    -1.24
    POSITIVE LOGITS
     also
    2.19
     it
    1.49
    in
    1.48
     there
    1.48
    żeli
    1.46
    糅
    1.44
    なども
    1.41
     that
    1.34
     although
    1.34
     tiež
    1.34
    Activations Density 0.046%

    No Known Activations