© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 53020
    Prev
    Next
    INDEX
    Explanations

    performance, significance, and texture discussions

    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
     وە
    0.50
     ivvu
    0.50
     گیر
    0.49
     pê
    0.48
     رجسٹریشن
    0.48
     atthakath
    0.48
    apanicola
    0.48
    퐈
    0.47
     thro
    0.46
     devono
    0.46
    POSITIVE LOGITS
    нк
    0.46
    us
    0.44
    amd
    0.44
    ં
    0.44
    os
    0.43
    on
    0.43
     slowly
    0.42
    イズ
    0.41
    ρκ
    0.40
    amt
    0.40
    Activations Density 0.003%

    No Known Activations