© 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. 34-GEMMASCOPE-RES-131K
    7. 57973
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and ideas

    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_34/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
     and
    -2.09
     nadru
    -1.76
    ?»
    -1.54
     trám
    -1.47
    tinh
    -1.45
    cô
    -1.44
    mô
    -1.43
     bolsos
    -1.42
     mochilas
    -1.41
     sandalias
    -1.41
    POSITIVE LOGITS
    ,
    1.55
    p
    1.46
    f
    1.45
    v
    1.44
    c
    1.39
    g
    1.37
    is
    1.34
    k
    1.30
    h
    1.29
    n
    1.28
    Activations Density 0.483%

    No Known Activations