© 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. 80247
    Prev
    Next
    INDEX
    Explanations

    psychiatric terms

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

    bypassing 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
     ನಗರ
    0.52
     Fewer
    0.48
    로는
    0.48
     уже
    0.47
     себе
    0.47
     cidades
    0.47
     নয়াদ
    0.46
    侨
    0.45
     نسخة
    0.45
     MEMBERS
    0.44
    POSITIVE LOGITS
     humoral
    0.56
     psychiatric
    0.55
     psychiatrist
    0.55
     pharmacological
    0.52
     Psychiatric
    0.52
     psychiatry
    0.49
     psychiatrists
    0.47
     apoptotic
    0.46
     antipsych
    0.46
     pharmac
    0.46
    Activations Density 0.000%

    No Known Activations