© 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. 40-GEMMASCOPE-2-RES-262K
    7. 32949
    Prev
    Next
    INDEX
    Explanations

    reporting sex assault hotline

    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_40_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
    "\
    0.39
     desempen
    0.37
     quale
    0.34
     desempeñ
    0.34
    َة
    0.34
     FGD
    0.34
     свер
    0.34
     зна
    0.33
     Guten
    0.33
     знай
    0.33
    POSITIVE LOGITS
    〗
    0.36
    IndexArray
    0.36
    issenschaft
    0.35
    ographie
    0.34
    etter
    0.34
    ၚ
    0.34
     ГӀ
    0.33
    person
    0.33
    ort
    0.33
    uft
    0.33
    Activations Density 0.014%

    No Known Activations