© 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. 4147
    Prev
    Next
    INDEX
    Explanations

    prioritize access and identification

    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
    forums
    0.47
     horror
    0.45
    forum
    0.45
     mayor
    0.43
     fiasco
    0.43
    centric
    0.43
    ၊
    0.43
    ող
    0.42
     or
    0.42
    fix
    0.42
    POSITIVE LOGITS
     площади
    0.51
     Fläche
    0.50
     NaOH
    0.47
     εργ
    0.46
     Frobenius
    0.46
    牛奶
    0.46
     вещества
    0.45
     welded
    0.44
     идентифика
    0.44
     сочета
    0.44
    Activations Density 0.000%

    No Known Activations