© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 9517
    Prev
    Next
    INDEX
    Explanations

    causing damage or harm

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

    damage and injury

    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
    preneurs
    0.39
    elyn
    0.38
     ২৬
    0.36
    ocrats
    0.36
    experiences
    0.35
    6
    0.34
     acts
    0.34
     Entrepreneurs
    0.34
    common
    0.34
    3
    0.34
    POSITIVE LOGITS
     delicate
    0.52
    損傷
    0.51
     teie
    0.49
     votre
    0.48
    损伤
    0.47
     vaš
    0.46
     iyong
    0.45
     danneggi
    0.45
    伤害
    0.45
     vaše
    0.45
    Activations Density 0.056%

    No Known Activations