© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 47428
    Prev
    Next
    INDEX
    Explanations

    riddle, pros, cons, weaknesses

    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_65k_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
     県
    0.46
     prudent
    0.45
     underscores
    0.43
    ('.');
    0.42
    簡単な
    0.42
     enhancers
    0.41
    県の
    0.41
     //</
    0.41
     speeds
    0.40
     USDA
    0.40
    POSITIVE LOGITS
    v
    0.54
    znam
    0.54
    يب
    0.53
     nazy
    0.50
    prayer
    0.49
    من
    0.48
    גיע
    0.48
    battery
    0.47
     gali
    0.47
    Confusion
    0.46
    Activations Density 0.002%

    No Known Activations