© 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. 99899
    Prev
    Next
    INDEX
    Explanations

    signing or verification

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

    public safety and healthcare

    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
     ต่าง
    0.50
     interstitiis
    0.49
    din
    0.48
     travaux
    0.48
     刺繍
    0.48
     Meal
    0.47
     連
    0.46
     antider
    0.46
     élytres
    0.46
    avasena
    0.46
    POSITIVE LOGITS
    就是
    0.43
     polémica
    0.42
    Signing
    0.41
     secretly
    0.40
    验证
    0.40
    回到
    0.40
     misguided
    0.40
    validate
    0.40
    შ
    0.40
    からは
    0.39
    Activations Density 0.000%

    No Known Activations