© 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-65K
    7. 4662
    Prev
    Next
    INDEX
    Explanations

    variables in equations or code

    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
    𒊬
    0.55
    бо
    0.55
    MORDOR
    0.55
     ɖ
    0.54
    HOBBIT
    0.54
     않고
    0.52
    스로
    0.52
    netHex
    0.52
    desPort
    0.51
     МО
    0.50
    POSITIVE LOGITS
    i
    0.73
    that
    0.70
    ia
    0.70
    an
    0.70
    t
    0.69
    a
    0.68
    the
    0.63
    we
    0.63
    Is
    0.62
    í
    0.62
    Activations Density 0.251%

    No Known Activations