© 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. 200126
    Prev
    Next
    INDEX
    Explanations

    USB or specific locations

    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
    وث
    0.40
    ORE
    0.39
     devoid
    0.39
    ند
    0.38
    бу
    0.37
    確
    0.37
    CONF
    0.37
    (-
    0.37
    盲
    0.35
     मार्ग
    0.35
    POSITIVE LOGITS
     iter
    0.56
     चम्म
    0.55
    ografi
    0.53
    larıyla
    0.52
     vaisse
    0.52
    uellement
    0.51
    ların
    0.51
    rades
    0.50
     detal
    0.50
    untamiento
    0.50
    Activations Density 0.000%

    No Known Activations