© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 163
    Prev
    Next
    INDEX
    Explanations

    time units and durations

    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
     not
    -1.55
     BaseEntity
    -1.48
    nother
    -1.40
    ufficient
    -1.35
     barva
    -1.33
     from
    -1.31
    ANTES
    -1.30
     bestens
    -1.30
     hitherto
    -1.30
     means
    -1.29
    POSITIVE LOGITS
     даже
    1.77
    }$,
    1.65
     of
    1.61
     gustaba
    1.46
    ми
    1.46
     после
    1.46
     навіть
    1.45
     его
    1.45
     gustó
    1.45
    甚至
    1.42
    Activations Density 0.037%

    No Known Activations