© 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. 185979
    Prev
    Next
    INDEX
    Explanations

    bubbling mud

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

    God, time phrases

    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
    抹茶
    0.61
    ᾗ
    0.50
    接觸
    0.48
    祝い
    0.48
    利用
    0.48
    renamiento
    0.48
    сти
    0.46
     Naruto
    0.46
    ಸ
    0.46
    თ
    0.46
    POSITIVE LOGITS
    ToSend
    0.49
     ασ
    0.49
     roost
    0.46
     nies
    0.45
     natura
    0.45
    ilmiştir
    0.44
     transmitter
    0.42
     quantified
    0.42
     ponad
    0.42
     وفا
    0.42
    Activations Density 0.000%

    No Known Activations