Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 84909
    Prev
    Next
    INDEX
    Explanations

    core aspects unchanged

    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
    kowej
    0.50
    芓
    0.46
    ینه
    0.46
    لے
    0.44
    まさに
    0.44
    धारणा
    0.43
     பல்கலை
    0.43
    𝓃
    0.43
    笑道
    0.43
     GTEST
    0.43
    POSITIVE LOGITS
    a
    0.55
    M
    0.52
    er
    0.50
    the
    0.50
    calculator
    0.48
    r
    0.46
    Monday
    0.46
    BL
    0.45
    calculation
    0.45
    u
    0.44
    Activations Density 0.000%

    No Known Activations