© 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. 41605
    Prev
    Next
    INDEX
    Explanations

    how not what

    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
     ዓይነ
    0.49
     ቀላል
    0.48
    ೇವಿನ
    0.48
    ┣
    0.48
     हाउ
    0.43
     стек
    0.42
     चिल्
    0.42
    PointSize
    0.42
    Bowling
    0.41
     ሥ
    0.41
    POSITIVE LOGITS
    am
    0.52
    ían
    0.44
    ors
    0.42
    ac
    0.42
     definitivamente
    0.42
     erhöhen
    0.42
    com
    0.41
    don
    0.41
     bruta
    0.41
    het
    0.41
    Activations Density 0.009%

    No Known Activations