© 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. 83822
    Prev
    Next
    INDEX
    Explanations

    urls and statements

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

    prompt manipulation and security vulnerabilities

    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
     огромное
    0.50
    poch
    0.49
     большое
    0.48
    ين
    0.48
     большой
    0.47
     погиб
    0.46
     कोणत्या
    0.46
    ០
    0.46
    thre
    0.45
    هم
    0.45
    POSITIVE LOGITS
    fact
    0.50
    返品
    0.49
     atk
    0.47
    atan
    0.46
    สาน
    0.45
     teclado
    0.43
    ट
    0.43
    elly
    0.43
     AT
    0.43
     fato
    0.43
    Activations Density 0.001%

    No Known Activations