© 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. 17852
    Prev
    Next
    INDEX
    Explanations

    file permissions

    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
     without
    0.48
     fără
    0.47
    abilir
    0.43
     ohne
    0.43
     F
    0.42
     Cummings
    0.42
     uten
    0.42
     $\
    0.41
    acetamol
    0.41
     Stevenson
    0.41
    POSITIVE LOGITS
    ્યૂ
    0.47
     лидер
    0.43
     observables
    0.42
    л
    0.42
     punctatis
    0.41
    ル
    0.41
    ?",
    0.41
     cuantit
    0.41
     trabajado
    0.40
     statistiques
    0.40
    Activations Density 0.001%

    No Known Activations