© 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. 11077
    Prev
    Next
    INDEX
    Explanations

    check for errors

    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
    ar
    0.51
    съ
    0.50
     farmer
    0.49
     farming
    0.47
     autres
    0.47
    ெ
    0.44
     notice
    0.42
     injury
    0.42
     image
    0.40
     kaw
    0.40
    POSITIVE LOGITS
     Vertrieb
    0.50
     Gespräch
    0.50
    <unused990>
    0.48
     necessaria
    0.48
    🌝
    0.47
     Mess
    0.47
    <unused236>
    0.46
    inska
    0.46
    失效
    0.45
     Versorgung
    0.44
    Activations Density 0.011%

    No Known Activations