© 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. 3824
    Prev
    Next
    INDEX
    Explanations

    code construction and data handling

    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
    quy
    0.38
    ку
    0.37
     целях
    0.37
     лице
    0.37
    <unused423>
    0.36
    kHz
    0.36
    ("#
    0.36
    စာ
    0.35
    intensité
    0.35
    боро
    0.35
    POSITIVE LOGITS
     reconstructed
    0.50
     struct
    0.49
     instantiated
    0.49
     reim
    0.48
     hybrid
    0.47
     verwenden
    0.47
     constructed
    0.47
     imported
    0.46
     constructor
    0.46
     structs
    0.46
    Activations Density 0.415%

    No Known Activations