© 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. 125358
    Prev
    Next
    INDEX
    Explanations

    sqlite, SQL, develop, transmit

    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
    ιο
    0.58
    ک
    0.53
    いる
    0.48
    黯
    0.46
    satz
    0.46
     gor
    0.46
    saint
    0.46
    sf
    0.45
    𝖙
    0.45
    skog
    0.44
    POSITIVE LOGITS
    Develop
    0.51
     превра
    0.51
     पाई
    0.48
    Lep
    0.48
     Lep
    0.48
     Purposes
    0.47
     Develop
    0.45
     develop
    0.45
     Operating
    0.45
     desarrolla
    0.45
    Activations Density 0.000%

    No Known Activations