© 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. 22005
    Prev
    Next
    INDEX
    Explanations

    vulnerabilities and attackers

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

    vulnerability versions

    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
    itabbam
    0.41
     आएगा
    0.40
    潵
    0.39
     корреспонд
    0.38
    貥
    0.38
    각
    0.37
     해석
    0.37
     ছুর
    0.36
     खरीदें
    0.36
    啦
    0.36
    POSITIVE LOGITS
     inflexible
    0.43
     hippocampal
    0.42
     alken
    0.41
     különböző
    0.41
     hypergly
    0.40
     naive
    0.40
     jedno
    0.40
     lacks
    0.39
     bilmi
    0.39
     ikke
    0.38
    Activations Density 0.001%

    No Known Activations