© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59125
    Prev
    Next
    INDEX
    Explanations

    Long layover

    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
    ドラ
    -0.83
    ⪯
    -0.82
    wla
    -0.77
     Could
    -0.75
    扱う
    -0.75
    leven
    -0.74
    fifths
    -0.74
     главным
    -0.74
     DECK
    -0.74
    Bij
    -0.73
    POSITIVE LOGITS
    érôme
    0.90
     yourself
    0.89
    uffle
    0.88
    mochila
    0.85
    ríguez
    0.85
     rencontré
    0.85
    ࿇
    0.84
    ujudkan
    0.82
     propone
    0.81
    personas
    0.81
    Activations Density 0.009%

    No Known Activations