© 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. 111126
    Prev
    Next
    INDEX
    Explanations

    predicts next word

    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
    𝓉
    0.45
    幡
    0.44
     طول
    0.44
     Helden
    0.43
     علشان
    0.43
     Hulk
    0.42
     다만
    0.42
    ron
    0.41
     Aufl
    0.41
    僖
    0.41
    POSITIVE LOGITS
     replaces
    0.48
     stressors
    0.45
     seeks
    0.44
    IGet
    0.43
     megsz
    0.42
    도의
    0.41
     disabilities
    0.41
     denotes
    0.41
    ointers
    0.41
     targets
    0.40
    Activations Density 0.007%

    No Known Activations