© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 30967
    Prev
    Next
    INDEX
    Explanations

    fibonacci numbers, prime numbers, or number calculations

    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
    ك
    0.61
    و
    0.57
    2
    0.55
     ноги
    0.52
    ו
    0.49
    1
    0.46
     первых
    0.46
     ιδια
    0.46
    ために
    0.46
     непосред
    0.44
    POSITIVE LOGITS
    us
    0.57
    фу
    0.52
     Brot
    0.52
    is
    0.50
    ing
    0.49
    ská
    0.49
     A
    0.48
    sap
    0.47
    습니다
    0.47
    boiled
    0.47
    Activations Density 0.144%

    No Known Activations