© 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. 200317
    Prev
    Next
    INDEX
    Explanations

    spatial relationships

    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
     gagal
    0.46
     multiplica
    0.46
    Ma
    0.45
     बटे
    0.44
     ל
    0.44
     akad
    0.43
     kanilang
    0.43
    weak
    0.42
     weakening
    0.42
     dictum
    0.41
    POSITIVE LOGITS
    erais
    0.52
     Castle
    0.44
    astricht
    0.44
     Bridges
    0.43
    <0x97>
    0.42
    oulders
    0.42
     Elbow
    0.41
     Penguins
    0.41
    在前
    0.40
    ến
    0.40
    Activations Density 0.006%

    No Known Activations