© 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. 16-GEMMASCOPE-2-RES-65K
    7. 3336
    Prev
    Next
    INDEX
    Explanations

    killing and harming

    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_16_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
    ES
    0.91
    HAS
    0.83
    TION
    0.82
    CC
    0.81
    W
    0.80
    AM
    0.80
    EN
    0.79
    ET
    0.77
    AS
    0.77
    AL
    0.77
    POSITIVE LOGITS
    .
    0.89
    ל
    0.87
    א
    0.87
     destroy
    0.86
     destroying
    0.85
    ร
    0.82
     killings
    0.81
     destruction
    0.80
    !”
    0.78
     kill
    0.77
    Activations Density 0.282%

    No Known Activations