© 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. 29-GEMMASCOPE-2-RES-16K
    7. 2247
    Prev
    Next
    INDEX
    Explanations

    civilian deaths or significant disaster

    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_29_width_16k_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
     threats
    0.71
     Threats
    0.70
     surprise
    0.68
     bass
    0.68
    運営
    0.68
    রাসের
    0.67
    Vanilla
    0.67
     反
    0.67
     punctul
    0.66
     dominant
    0.64
    POSITIVE LOGITS
     casualties
    2.04
     fatalities
    2.03
     deaths
    1.89
     victims
    1.84
     innocent
    1.76
    casualties
    1.75
    deaths
    1.73
     lives
    1.66
     жерт
    1.65
    Deaths
    1.63
    Activations Density 0.256%

    No Known Activations