© 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. 108490
    Prev
    Next
    INDEX
    Explanations

    self, single, existence

    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
     रोजी
    0.47
    🕕
    0.46
    oksatta
    0.46
    🕤
    0.46
     Dokl
    0.45
     выйти
    0.45
     जीवन
    0.43
    🕣
    0.43
    शाही
    0.43
     Rodr
    0.43
    POSITIVE LOGITS
    ER
    0.56
    4
    0.51
    IGER
    0.48
    ic
    0.48
    6
    0.48
    5
    0.47
    ME
    0.46
    8
    0.46
    TE
    0.45
    ERS
    0.45
    Activations Density 0.001%

    No Known Activations