© 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. 34-GEMMASCOPE-RES-131K
    4. 2923
    Prev
    Next
    INDEX
    Explanations

    frequency and repetition

    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
     of
    -1.62
     and
    -1.35
     from
    -1.24
     that
    -1.23
     which
    -1.16
     based
    -1.05
     continually
    -0.96
     отвечает
    -0.93
     taken
    -0.93
     maintained
    -0.91
    POSITIVE LOGITS
     подряд
    1.40
    times
    1.01
    komend
    1.00
    würfe
    0.96
     veces
    0.95
     (!)
    0.94
     אֶ
    0.94
    课程
    0.94
     Pokies
    0.94
    法国
    0.93
    Activations Density 0.030%

    No Known Activations