© 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. 200511
    Prev
    Next
    INDEX
    Explanations

    boundaries, but

    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
    ἁ
    0.51
    禦
    0.48
    D
    0.48
    security
    0.47
    ングル
    0.46
    ἄ
    0.46
    might
    0.44
    癮
    0.43
    норий
    0.42
    crime
    0.42
    POSITIVE LOGITS
     differenza
    0.53
     textarea
    0.52
     rup
    0.52
     won
    0.51
     italiana
    0.50
     Italians
    0.49
     option
    0.48
     înt
    0.48
     empleados
    0.48
     faptul
    0.48
    Activations Density 0.003%

    No Known Activations