© 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. 113434
    Prev
    Next
    INDEX
    Explanations

    categories or specific details

    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
     data
    0.53
     P
    0.50
     key
    0.50
     elev
    0.50
    key
    0.49
    TG
    0.48
     EHR
    0.48
     GR
    0.48
     HIV
    0.47
     fin
    0.46
    POSITIVE LOGITS
    yı
    0.53
     sobretudo
    0.50
     Από
    0.50
    Przeczytaj
    0.49
     કરવાનું
    0.49
    逶
    0.48
    窸
    0.48
    がありますが
    0.46
     સમય
    0.46
    ̀u
    0.46
    Activations Density 0.000%

    No Known Activations