© 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. 12870
    Prev
    Next
    INDEX
    Explanations

    break down

    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
    <0x80>
    0.61
    ０
    0.61
    E
    0.60
     }^{
    0.58
     vudd
    0.58
    0
    0.57
    PAY
    0.55
    D
    0.55
     fevereiro
    0.54
    H
    0.54
    POSITIVE LOGITS
     Breaking
    1.19
     Break
    1.13
     breaking
    1.11
     break
    1.05
     Breaks
    1.02
    Breaking
    1.02
    breaking
    0.99
    breakable
    0.96
     breaks
    0.95
    Break
    0.92
    Activations Density 0.090%

    No Known Activations