© 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. 31-GEMMASCOPE-2-RES-262K
    7. 201359
    Prev
    Next
    INDEX
    Explanations

    description of harmful content

    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
     हूं
    0.50
    с
    0.48
    у
    0.47
    ре
    0.46
    ја
    0.46
    姩
    0.46
    є
    0.45
     বছর
    0.44
     ofrece
    0.44
    г
    0.44
    POSITIVE LOGITS
    }\,\
    0.47
     arrhythmias
    0.45
     haemorrh
    0.45
     arrhyth
    0.43
     stomachs
    0.43
     Schwarzschild
    0.43
     scarring
    0.42
    liness
    0.42
     infarct
    0.42
     काव्य
    0.42
    Activations Density 0.005%

    No Known Activations