© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 102364
    Prev
    Next
    INDEX
    Explanations

    Attack patterns and vectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entreprise
    0.41
     waarom
    0.40
    ーツ
    0.39
     waarbij
    0.39
     چیک
    0.39
     enfin
    0.39
    ῃ
    0.38
     específ
    0.38
     adresse
    0.38
     asfalt
    0.37
    POSITIVE LOGITS
    ERI
    0.41
    Baba
    0.40
    adhy
    0.40
     Prat
    0.39
    Attrib
    0.39
    Sentinel
    0.39
    강
    0.38
    eso
    0.38
    вания
    0.37
    Xs
    0.37
    Activations Density 0.000%

    No Known Activations