© 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-65K
    7. 65203
    Prev
    Next
    INDEX
    Explanations

    options or alternatives

    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_65k_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
    ನ್ನು
    0.43
     prolog
    0.42
     까
    0.42
    ):
    0.40
    hesk
    0.40
    CHEAT
    0.40
    aston
    0.39
     behaved
    0.39
    रील
    0.39
     dai
    0.39
    POSITIVE LOGITS
     मटे
    0.46
    Armor
    0.45
     acquaintances
    0.43
     числе
    0.43
     सात
    0.42
     armor
    0.41
     ጠ
    0.41
     Хабаров
    0.40
     шам
    0.39
    琰
    0.39
    Activations Density 0.002%

    No Known Activations