© 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. 168775
    Prev
    Next
    INDEX
    Explanations

    provides more

    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
    欵
    0.45
    وفي
    0.43
    quisitions
    0.42
     lagged
    0.42
    igte
    0.41
    ات
    0.41
    《
    0.41
     conclure
    0.40
     instigated
    0.40
     Weltkrieg
    0.40
    POSITIVE LOGITS
     penguins
    0.44
     nast
    0.43
    :");
    0.43
    วี
    0.43
     kilogram
    0.43
    Separator
    0.42
    }"),
    0.42
    par
    0.42
    мар
    0.42
    mil
    0.41
    Activations Density 0.001%

    No Known Activations