© 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. 157164
    Prev
    Next
    INDEX
    Explanations

    minutes from time

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

    stable demographic, consumption, palatable fungal

    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
    Nutrition
    0.50
    制品
    0.49
    主机
    0.48
    例
    0.48
    溱
    0.47
     inventing
    0.47
    屼
    0.47
    举
    0.47
    晹
    0.47
    为什么
    0.46
    POSITIVE LOGITS
     longstanding
    0.44
     ((
    0.43
     mortg
    0.41
    ्वान
    0.41
     dampened
    0.40
    及び
    0.39
     denim
    0.39
     recon
    0.39
     atas
    0.39
     twenty
    0.39
    Activations Density 0.001%

    No Known Activations