© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 120160
    Prev
    Next
    INDEX
    Explanations

    symbols and variables

    np_acts-logits-general · gemini-2.5-flash-lite

    subscripted variables (like $a_n$, $b_i$, $C_N$) in mathematical notation.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     and
    -2.83
     because
    -1.86
     produisons
    -1.71
    COLOG
    -1.54
    ↵
    -1.53
    uminense
    -1.53
    でしたが
    -1.52
    uleiro
    -1.50
     müßte
    -1.50
     also
    -1.49
    POSITIVE LOGITS
     of
    4.69
     our
    2.31
    玙
    2.30
    盦
    2.30
     it
    2.11
    なるべく
    2.08
     alcune
    2.00
     the
    1.97
    えっ
    1.89
    colgante
    1.88
    Activations Density 0.043%

    No Known Activations