© 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. 57217
    Prev
    Next
    INDEX
    Explanations

    makes breakthroughs simple

    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
    적이
    0.44
     informacije
    0.44
    нуу
    0.41
    فع
    0.41
     Manit
    0.39
    Ú
    0.39
    喷
    0.39
    ⟣
    0.39
     breathe
    0.38
    ስቃሴ
    0.38
    POSITIVE LOGITS
    ad
    0.47
    h
    0.45
    ísima
    0.45
    gov
    0.44
     கட்டு
    0.43
    chai
    0.43
     EMPLOY
    0.41
    orship
    0.40
    leo
    0.40
     prescribing
    0.40
    Activations Density 0.003%

    No Known Activations