© 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. 51003
    Prev
    Next
    INDEX
    Explanations

    safety, desktop, gas, car

    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
    0.52
    sar
    0.51
    a
    0.47
     risultati
    0.46
    sac
    0.45
    s
    0.44
    (
    0.44
     एक
    0.43
    lic
    0.43
    skip
    0.43
    POSITIVE LOGITS
     wobec
    0.47
    ActionButton
    0.46
    িগ
    0.46
    ತ್ರೆ
    0.46
     QtCore
    0.46
     النرويج
    0.45
    ))`
    0.45
    ర్థి
    0.44
    𝐈
    0.44
    ProjectType
    0.43
    Activations Density 0.000%

    No Known Activations