© 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. 112965
    Prev
    Next
    INDEX
    Explanations

    manual creation, tools, or actions

    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
    ために
    0.88
    ক
    0.68
    žne
    0.66
    ग्विजय
    0.66
    ため
    0.65
    자
    0.65
     étudiants
    0.64
    uaje
    0.63
    나
    0.61
     falsely
    0.61
    POSITIVE LOGITS
     hand
    1.04
     Hand
    1.04
     (
    0.99
     HAND
    0.89
     käs
    0.89
     Hands
    0.89
     hands
    0.80
    ing
    0.79
     hånd
    0.78
    Hand
    0.77
    Activations Density 0.032%

    No Known Activations