© 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. 128461
    Prev
    Next
    INDEX
    Explanations

    safeguard interests and identify risks

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

    safety and techniques

    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
    (
    0.68
    /
    0.63
    )
    0.57
    {\
    0.56
    ↵↵
    0.51
    (\
    0.48
    {
    0.48
     \
    0.48
    -{
    0.48
    )(
    0.47
    POSITIVE LOGITS
    addena
    0.56
     உயரம்
    0.53
     сохра
    0.51
     узна
    0.51
     ඔවුන්
    0.47
     bekommen
    0.46
     ragazzo
    0.46
     quả
    0.46
     সভাপ
    0.46
    ковым
    0.46
    Activations Density 0.000%

    No Known Activations