© 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. 194677
    Prev
    Next
    INDEX
    Explanations

    other language content

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

    ENTRY FUNCTION ACTIVATION

    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
     사이즈
    0.47
     likely
    0.47
     credibility
    0.46
     cutaneous
    0.46
     JI
    0.46
     쉽
    0.46
     Trần
    0.46
     Pulmonary
    0.45
     গিয়েছিল
    0.44
     निकालने
    0.44
    POSITIVE LOGITS
    в
    0.56
    ק
    0.56
    ли
    0.54
    ма
    0.54
    да
    0.53
    ق
    0.53
    ام
    0.52
    ви
    0.52
     lucru
    0.51
    ъ
    0.50
    Activations Density 0.000%

    No Known Activations