© 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. 79359
    Prev
    Next
    INDEX
    Explanations

    medic alert bracelet

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

    Understanding the situation

    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
    ﻜ
    0.51
     Fad
    0.45
     Т
    0.44
    ġ
    0.44
    AT
    0.44
     ECA
    0.42
    І
    0.42
    ادة
    0.42
    Burger
    0.42
    ജി
    0.42
    POSITIVE LOGITS
    羪
    0.57
     rootView
    0.53
    晎
    0.52
     субъек
    0.48
    UIColor
    0.48
    ською
    0.47
     вироб
    0.47
    वरों
    0.47
     underm
    0.46
    diendo
    0.46
    Activations Density 0.000%

    No Known Activations