© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 46398
    Prev
    Next
    INDEX
    Explanations

    examples, definitions, or mathematical series

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alakip
    0.50
     ભાગ
    0.47
    𝐫
    0.47
     வழிபாடு
    0.45
    陸
    0.44
     ର
    0.44
     يخ
    0.44
     ثانوي
    0.43
     ट्रांसपोर्ट
    0.43
    ங்களாக
    0.43
    POSITIVE LOGITS
     infus
    0.49
     Kunde
    0.46
     whence
    0.45
    B
    0.45
     heady
    0.44
     Monate
    0.44
    诞
    0.44
     iPhone
    0.44
     fromage
    0.43
     Erde
    0.43
    Activations Density 0.011%

    No Known Activations