© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 208559
    Prev
    Next
    INDEX
    Explanations

    providing fun historical details

    np_acts-logits-general · gemini-2.5-flash-lite

    Robb Stark's situation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     सशस्त्र
    0.52
     कदा
    0.50
     प्रचलित
    0.48
     हज
    0.48
     Boil
    0.47
     adverb
    0.46
    Ｕ
    0.45
    カート
    0.45
    malı
    0.44
     मद्
    0.44
    POSITIVE LOGITS
    steins
    0.56
    aronder
    0.46
    ભાગ
    0.46
    ilish
    0.42
    permissions
    0.41
     szk
    0.41
     thuis
    0.41
    廊
    0.41
    ürü
    0.40
    的是
    0.40
    Activations Density 0.001%

    No Known Activations