© 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. 93784
    Prev
    Next
    INDEX
    Explanations

    code structure, technical terms

    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
    Ꮞ
    0.50
    ಾಗಿತ್ತು
    0.49
    ავი
    0.49
    瑋
    0.48
    COMDAT
    0.48
    濰
    0.46
    བྱ
    0.45
    που
    0.45
    ၻ
    0.45
    lav
    0.44
    POSITIVE LOGITS
    ø
    0.47
     continúa
    0.46
     resisted
    0.45
     Brings
    0.45
     dares
    0.44
    poon
    0.44
    бор
    0.43
     неодно
    0.43
     brought
    0.43
     Antonio
    0.43
    Activations Density 0.000%

    No Known Activations