© 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. 138997
    Prev
    Next
    INDEX
    Explanations

    somewhat controversial

    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
     chorizo
    0.53
     invertebr
    0.48
    थोरो
    0.46
    geqq
    0.46
    iscid
    0.46
    ख्ती
    0.46
    ганда
    0.46
    卅
    0.46
    ṱ
    0.45
     investigación
    0.45
    POSITIVE LOGITS
    to
    0.64
     to
    0.60
    ic
    0.55
    (
    0.51
     bardzo
    0.45
    ile
    0.45
    ey
    0.44
    ania
    0.44
    Deadline
    0.44
     ways
    0.44
    Activations Density 0.016%

    No Known Activations