© 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. 26853
    Prev
    Next
    INDEX
    Explanations

    html meta charset

    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
    bic
    0.48
     Comp
    0.42
     Dei
    0.42
     Depreciation
    0.41
     Effect
    0.41
     Meine
    0.41
    ﺑ
    0.40
     Fiscal
    0.40
    enteuer
    0.39
     Market
    0.39
    POSITIVE LOGITS
    ulière
    0.40
    ihat
    0.38
    /_
    0.38
     आस्था
    0.38
     irregularities
    0.38
     crashes
    0.38
    தன
    0.38
    |_
    0.38
    ولوج
    0.37
    ানি
    0.37
    Activations Density 0.000%

    No Known Activations