© 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. 73162
    Prev
    Next
    INDEX
    Explanations

    S. , until. , Street. , shaft. , Amendment of

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

    attempt to bypass safety filters

    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
    Considering
    0.56
    陝
    0.48
    この
    0.48
    Scorch
    0.47
    ))$,
    0.46
    By
    0.46
    Adj
    0.45
    )$,
    0.45
    deleteOne
    0.45
    Now
    0.44
    POSITIVE LOGITS
     silam
    0.50
     koa
    0.49
    ier
    0.49
     isl
    0.48
     oma
    0.48
     russia
    0.48
     hust
    0.47
     mille
    0.47
     equil
    0.46
    ieu
    0.46
    Activations Density 0.001%

    No Known Activations