© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84006
    Prev
    Next
    INDEX
    Explanations

    recollection of past events

    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
    <i>
    -2.80
    AL
    -2.69
            
    -2.64
    𓋼
    -2.45
    The
    -2.45
    ER
    -2.38
    𝐧
    -2.31
    An
    -2.28
    In
    -2.22
     foremost
    -2.22
    POSITIVE LOGITS
    寕
    2.52
     ‘‘
    2.28
    n
    2.23
     ‘’
    2.20
    siones
    2.14
     Süden
    2.08
    Showcase
    2.08
    ectady
    2.06
     diseñ
    2.02
     únicamente
    2.02
    Activations Density 0.000%

    No Known Activations