© 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. 34-GEMMASCOPE-RES-131K
    7. 63894
    Prev
    Next
    INDEX
    Explanations

    non refundable, necessary action, collegiate field

    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
     wielu
    -0.91
     numerose
    -0.88
     numerosi
    -0.85
     sufrido
    -0.85
     początku
    -0.85
     mnoho
    -0.84
     ślub
    -0.82
    和她
    -0.82
     jedynie
    -0.81
    凄く
    -0.81
    POSITIVE LOGITS
    ϳ
    0.90
    acyj
    0.89
    😱
    0.89
    versies
    0.88
    🎤
    0.86
    urysty
    0.84
    zzlement
    0.84
    feito
    0.82
    неров
    0.82
     demoral
    0.81
    Activations Density 0.004%

    No Known Activations