© 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. 13912
    Prev
    Next
    INDEX
    Explanations

    super.onCreate

    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
     ketchup
    0.41
    Brow
    0.40
     xyl
    0.39
     dichos
    0.38
     dicho
    0.38
     féd
    0.37
    cort
    0.36
    醬
    0.36
    ハン
    0.36
     agricole
    0.36
    POSITIVE LOGITS
    operations
    0.37
    autoconfigure
    0.36
    onCreate
    0.35
    ();
    0.34
     ਆਪਣ
    0.34
    ;.
    0.34
    ubation
    0.34
    ("");
    0.33
    emplates
    0.33
    operatively
    0.33
    Activations Density 0.000%

    No Known Activations