© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 233836
    Prev
    Next
    INDEX
    Explanations

    killing or being killed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_32_width_262k_l0_small_affine
    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
     внутренних
    0.48
    Murder
    0.41
     vernacular
    0.41
     pak
    0.40
    murder
    0.40
     उर्दू
    0.39
    豫
    0.38
     slaying
    0.38
    ]$-
    0.37
    部门
    0.37
    POSITIVE LOGITS
     създа
    0.40
     consigned
    0.40
     flipped
    0.40
     created
    0.38
     bef
    0.38
     Created
    0.38
     fou
    0.38
    ຟ
    0.37
     intercepted
    0.36
    創
    0.36
    Activations Density 0.000%

    No Known Activations