© 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. 111272
    Prev
    Next
    INDEX
    Explanations

    global understanding

    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
    on
    0.54
    and
    0.53
    e
    0.51
    as
    0.48
    Device
    0.45
    et
    0.44
    मा
    0.44
    스
    0.44
     eff
    0.44
     bereaved
    0.43
    POSITIVE LOGITS
     คอม
    0.54
     אפ
    0.49
     globale
    0.48
     Aussi
    0.47
    คอม
    0.47
     อะไร
    0.46
     Prozess
    0.46
     Chois
    0.46
    琹
    0.46
    ocado
    0.45
    Activations Density 0.000%

    No Known Activations