© 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. 138632
    Prev
    Next
    INDEX
    Explanations

    often, usually, data

    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
    c
    0.55
    s
    0.54
    ים
    0.51
    ༦
    0.50
    К
    0.49
     чер
    0.46
     увла
    0.46
    i
    0.46
    ла
    0.46
    d
    0.46
    POSITIVE LOGITS
     tessuto
    0.48
     높아
    0.44
    ômes
    0.44
    তনা
    0.44
     cooker
    0.43
     accueill
    0.43
     fabricación
    0.43
     تیاری
    0.42
     novedades
    0.41
    MeV
    0.41
    Activations Density 0.004%

    No Known Activations