© 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. 23730
    Prev
    Next
    INDEX
    Explanations

    book shopresolutionsDVD Store

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

    responsible for conditions

    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
     revue
    0.47
     полноцен
    0.46
     IMM
    0.45
     Immune
    0.43
    ='
    0.42
     adapté
    0.42
     gepubliceerd
    0.42
     invasive
    0.41
     noget
    0.41
     Drake
    0.41
    POSITIVE LOGITS
     달려
    0.57
    ﺰ
    0.50
    leaders
    0.48
     സാഹ
    0.48
     संख्या
    0.46
    لها
    0.46
     desigual
    0.46
    ന്നും
    0.46
     男女
    0.46
    sof
    0.46
    Activations Density 0.001%

    No Known Activations