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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 19035
    Prev
    Next
    INDEX
    Explanations

    difficulty description

    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
     
    0.33
     also
    0.30
    on
    0.30
     those
    0.30
    也会
    0.29
    D
    0.28
     Freeman
    0.28
     same
    0.27
     Soap
    0.27
    ym
    0.27
    POSITIVE LOGITS
     എന്നിവ
    0.39
     എന്നീ
    0.39
     ஆகிய
    0.36
    Შ
    0.36
     ?”
    0.35
     novoProduto
    0.35
     observaciones
    0.35
    ੭
    0.35
    <unused649>
    0.35
     மட்டும்
    0.35
    Activations Density 0.188%

    No Known Activations