© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 25605
    Prev
    Next
    INDEX
    Explanations

    results from

    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
    ៧
    0.50
     మరియు
    0.47
     whakar
    0.47
     hona
    0.46
     Disputes
    0.46
     आणि
    0.46
    arze
    0.45
    ສົ
    0.44
    硏
    0.44
    拨款
    0.43
    POSITIVE LOGITS
     комп
    0.47
    queued
    0.44
     će
    0.43
    ુક
    0.43
     défaut
    0.42
     off
    0.41
    uración
    0.41
    from
    0.40
    Camping
    0.40
    ipso
    0.39
    Activations Density 0.001%

    No Known Activations