© 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. 11506
    Prev
    Next
    INDEX
    Explanations

    which means

    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
    ometime
    0.41
     एवं
    0.38
     ಅನೇಕ
    0.37
     जेव्हा
    0.36
     സാധാരണ
    0.35
     /
    0.35
    brough
    0.35
     ۱
    0.35
    ногие
    0.35
    小さい
    0.35
    POSITIVE LOGITS
     enhances
    0.43
     所以
    0.37
     opts
    0.37
     बेहतर
    0.36
     empowers
    0.36
    空间的
    0.35
     spaceShip
    0.35
     sculptural
    0.35
     enhance
    0.35
     중심으로
    0.35
    Activations Density 0.127%

    No Known Activations