© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7257
    Prev
    Next
    INDEX
    Explanations

    ability in languages

    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
     從
    0.45
     kerusakan
    0.44
     pengg
    0.44
    스와
    0.44
     ಕ್ಷ
    0.44
     boobs
    0.43
     wrecked
    0.42
    TypeId
    0.42
    غراف
    0.42
     breasts
    0.41
    POSITIVE LOGITS
    outcome
    0.44
    peripheral
    0.43
    ႅ
    0.40
    constant
    0.40
     impair
    0.40
    consumer
    0.39
    momentum
    0.39
    .
    0.39
     peripheral
    0.38
    fight
    0.38
    Activations Density 0.000%

    No Known Activations