© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 20798
    Prev
    Next
    INDEX
    Explanations

    perpetrator, attacker, culprit, assailant, thief

    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_262k_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
    P
    0.77
    ー
    0.75
    ER
    0.74
    C
    0.73
    S
    0.71
    н
    0.71
    بر
    0.71
    B
    0.71
    ন
    0.70
    R
    0.69
    POSITIVE LOGITS
     perpetrators
    0.74
     perpetrator
    0.70
     assail
    0.70
     culprits
    0.68
     attackers
    0.66
     assailant
    0.62
     burgl
    0.62
     athletic
    0.61
     vant
    0.61
     thieves
    0.61
    Activations Density 0.022%

    No Known Activations