© 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-262K
    4. 13738
    Prev
    Next
    INDEX
    Explanations

    class, pay, particles

    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
     and
    0.43
     has
    0.42
    &
    0.41
     neurolog
    0.41
     dramatically
    0.40
     cres
    0.39
     diet
    0.39
     relationships
    0.39
     genes
    0.39
     confidently
    0.39
    POSITIVE LOGITS
     оплаты
    0.46
    逅
    0.44
     آفیسر
    0.43
     கண்காணி
    0.43
     सकेगा
    0.42
     prepd
    0.41
    ]).
    0.40
    verick
    0.40
    屶
    0.40
     ລັບ
    0.39
    Activations Density 0.010%

    No Known Activations