© 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. 17019
    Prev
    Next
    INDEX
    Explanations

    technical code and concepts

    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
    ak
    1.17
    א
    1.10
    on
    1.08
    f
    1.02
    as
    1.02
    et
    1.00
    is
    1.00
    ل
    0.97
    ed
    0.93
    are
    0.93
    POSITIVE LOGITS
     humanos
    0.58
     pequeños
    0.58
     económicos
    0.58
     práct
    0.55
     gratuitos
    0.55
    oksatta
    0.54
     volontà
    0.54
     revital
    0.53
     políticos
    0.52
     compuestos
    0.52
    Activations Density 0.985%

    No Known Activations