© 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. 84715
    Prev
    Next
    INDEX
    Explanations

    names and nationalities

    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
    -3.25
    having
    -2.78
    ⩥
    -2.77
    have
    -2.67
     verbess
    -2.63
     Increased
    -2.55
    蟥
    -2.50
     blaue
    -2.45
     Changed
    -2.44
    selben
    -2.42
    POSITIVE LOGITS
    舁
    2.42
    檠
    2.28
     regardé
    2.27
    銕
    2.25
    埸
    2.17
     superbly
    2.14
     essayé
    2.11
    栳
    2.08
    стройства
    2.05
    ﾚ
    2.05
    Activations Density 0.011%

    No Known Activations