© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 3961
    Prev
    Next
    INDEX
    Explanations

    resource identifiers

    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
    Unifier
    0.33
    饴
    0.33
     dialects
    0.32
    ండ్లు
    0.31
     constellations
    0.30
     toroidal
    0.29
     ядра
    0.29
     必要
    0.29
     diastere
    0.29
    俎
    0.29
    POSITIVE LOGITS
    ukum
    0.33
    am
    0.32
    ŝ
    0.32
     similares
    0.31
    nsan
    0.30
    ray
    0.30
    ź
    0.30
    ov
    0.30
    その他の
    0.29
    anc
    0.29
    Activations Density 0.170%

    No Known Activations