© 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. 138946
    Prev
    Next
    INDEX
    Explanations

    describe actions or states

    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
     infinito
    0.53
     invasions
    0.52
     вой
    0.51
     --->
    0.51
     À
    0.49
     цены
    0.48
     industrious
    0.48
     larva
    0.47
     corrosive
    0.47
     అవకాశ
    0.47
    POSITIVE LOGITS
    b
    0.43
    ườ
    0.42
    Liqu
    0.41
    g
    0.41
    Chronic
    0.40
    Write
    0.40
    Filter
    0.40
    Rite
    0.40
    Sodium
    0.40
    Fluor
    0.39
    Activations Density 0.001%

    No Known Activations