© 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-262K
    7. 26079
    Prev
    Next
    INDEX
    Explanations

    often free

    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_262k_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
    徸
    0.47
     ار
    0.46
     دری
    0.46
    囦
    0.45
     পরিবেশ
    0.44
     bisogno
    0.44
     वेग
    0.44
    玨
    0.44
     empê
    0.43
    奻
    0.43
    POSITIVE LOGITS
    0
    0.54
    G
    0.54
    са
    0.51
    oh
    0.50
    az
    0.49
    та
    0.47
    &
    0.47
     Faça
    0.47
    JE
    0.45
    OP
    0.45
    Activations Density 0.001%

    No Known Activations