© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46876
    Prev
    Next
    INDEX
    Explanations

    Toy Story

    np_acts-logits-general · gemini-2.5-flash-lite

    examples, metaphorical, developed, numbers, skip

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    뎌
    0.58
    áv
    0.54
    ifting
    0.49
     steadfast
    0.47
    écie
    0.47
    effic
    0.46
    efficacy
    0.46
    today
    0.46
    kay
    0.46
    goal
    0.46
    POSITIVE LOGITS
    ڌ
    0.45
     मनोवैज्ञानिक
    0.45
     English
    0.44
     binh
    0.44
     azonban
    0.42
     culmin
    0.41
     Musical
    0.41
     Asalamualaikum
    0.41
    లిన
    0.41
    л
    0.41
    Activations Density 0.000%

    No Known Activations