© 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. 22-GEMMASCOPE-RES-131K
    7. 70978
    Prev
    Next
    INDEX
    Explanations

    a type of

    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_22/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
     throbbing
    -0.97
    particularly
    -0.95
    のもの
    -0.94
    EUROPA
    -0.93
    ⛦
    -0.92
     devine
    -0.91
     namens
    -0.90
    Aries
    -0.90
    骂
    -0.90
    囑
    -0.89
    POSITIVE LOGITS
     a
    1.29
     where
    1.20
     from
    1.09
     semacam
    1.09
     an
    1.08
    렀
    1.07
     basically
    1.02
     viņ
    0.98
     būt
    0.94
     when
    0.93
    Activations Density 0.067%

    No Known Activations