© 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. 71171
    Prev
    Next
    INDEX
    Explanations

    asset, resources, or usage

    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
    again
    0.49
     present
    0.48
    content
    0.46
    enter
    0.45
    initi
    0.45
    o
    0.43
    at
    0.42
    port
    0.42
    ag
    0.42
    ond
    0.42
    POSITIVE LOGITS
     کچھ
    0.55
    梟
    0.53
     szko
    0.52
     educación
    0.52
     Educación
    0.49
     Escuela
    0.49
     escuela
    0.48
    '
    0.48
     batería
    0.48
     पार्किंग
    0.48
    Activations Density 0.008%

    No Known Activations