© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 8326
    Prev
    Next
    INDEX
    Explanations

    harming others or self

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_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
     of
    0.87
     from
    0.78
    จาก
    0.76
     with
    0.73
     in
    0.70
    ate
    0.69
    ด้วย
    0.68
    '
    0.67
     by
    0.65
     efforts
    0.64
    POSITIVE LOGITS
     being
    0.98
    being
    0.88
     essere
    0.84
     BEING
    0.81
     étant
    0.80
    Being
    0.79
     Being
    0.78
    čno
    0.73
     fiind
    0.72
     आल्सो
    0.71
    Activations Density 0.120%

    No Known Activations