© 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. 74847
    Prev
    Next
    INDEX
    Explanations

    dice rolls and quantities

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

    add modifiers

    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
    ।
    0.45
     言っ
    0.44
    men
    0.43
     सूची
    0.42
    totalPages
    0.41
    list
    0.41
    rest
    0.40
     pell
    0.40
    낍
    0.40
    elles
    0.40
    POSITIVE LOGITS
     Vielzahl
    0.53
     mochila
    0.47
     görünt
    0.47
     nossos
    0.46
     birçok
    0.46
    نوات
    0.46
     العديد
    0.46
     generando
    0.46
     nossas
    0.45
     robuste
    0.45
    Activations Density 0.005%

    No Known Activations