© 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. 189704
    Prev
    Next
    INDEX
    Explanations

    specific words following punctuation

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

    probability, likelihood, methodologies

    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
    딩
    0.48
     pře
    0.44
     inline
    0.44
     samples
    0.43
    nts
    0.43
    处
    0.43
    емости
    0.42
     перейти
    0.42
    准备
    0.42
     edad
    0.42
    POSITIVE LOGITS
     saddened
    0.48
    पुट
    0.45
     worrisome
    0.45
     ஆம்
    0.43
    ૧
    0.43
    canceled
    0.42
     pitiful
    0.42
     काय
    0.42
    मह
    0.42
    Þ
    0.42
    Activations Density 0.000%

    No Known Activations