© 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. 76652
    Prev
    Next
    INDEX
    Explanations

    these, first, supreme

    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
     frecuencia
    0.48
    ะ
    0.44
    ྒྱ
    0.42
    ג
    0.41
    ги
    0.41
    ICAL
    0.41
    Existe
    0.41
    ADOR
    0.40
    गा
    0.40
    argsort
    0.40
    POSITIVE LOGITS
     優
    0.52
     Supreme
    0.51
     这些
    0.51
     These
    0.47
     これらの
    0.46
     protože
    0.45
     dev
    0.45
     પ્રથમ
    0.45
     res
    0.45
     prim
    0.44
    Activations Density 0.005%

    No Known Activations