© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92483
    Prev
    Next
    INDEX
    Explanations

    malware injection uncover valuable

    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/layer_31_width_262k_l0_medium
    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
    -
    0.50
    -}
    0.48
    /
    0.46
    -=
    0.46
    enumerate
    0.45
    ieve
    0.45
    -}$
    0.44
    :-)
    0.44
    uke
    0.43
    }--\
    0.43
    POSITIVE LOGITS
     вызывает
    0.50
    激活
    0.50
    י
    0.49
     stadion
    0.49
     Type
    0.48
     laughing
    0.48
    啇
    0.47
    ো
    0.46
     laughed
    0.45
    רי
    0.45
    Activations Density 0.003%

    No Known Activations