© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 106742
    Prev
    Next
    INDEX
    Explanations

    stranglers episodes reporter gallery dol football

    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
    いつ
    -0.82
     слу
    -0.75
     キャラクター
    -0.73
     tritium
    -0.71
    wnętr
    -0.71
     utente
    -0.71
    páns
    -0.70
    viana
    -0.69
    而且
    -0.69
     challeng
    -0.69
    POSITIVE LOGITS
     Metodo
    0.75
     환
    0.74
     bero
    0.73
     gar
    0.73
     wysy
    0.72
     adore
    0.72
    什么呢
    0.72
     clo
    0.71
    ждане
    0.71
    煎
    0.71
    Activations Density 0.040%

    No Known Activations