© 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. 10-GEMMASCOPE-RES-131K
    7. 99928
    Prev
    Next
    INDEX
    Explanations

    civil society and liberties

    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
     the
    -2.34
    of
    -1.88
     as
    -1.86
     jahre
    -1.69
     some
    -1.65
     many
    -1.63
     we
    -1.58
    ancient
    -1.55
     our
    -1.54
     several
    -1.54
    POSITIVE LOGITS
    Ꮉ
    2.05
    ௅
    2.00
    他的
    1.98
    這
    1.95
    ޏ
    1.94
    桖
    1.89
    這是
    1.83
    今日は
    1.75
    (!__
    1.74
    ቍ
    1.73
    Activations Density 0.005%

    No Known Activations