© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 5380
    Prev
    Next
    INDEX
    Explanations

    policy against involvement

    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_all/layer_41_width_262k_l0_big
    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
     instantaneous
    0.49
    rupted
    0.46
    ิ้น
    0.46
    Ҥ
    0.46
    atenated
    0.45
     physiological
    0.45
    क्स
    0.44
    瘩
    0.44
     instantaneously
    0.44
     datetime
    0.44
    POSITIVE LOGITS
     abstain
    1.06
     avoided
    1.02
     avoid
    1.02
     abst
    1.01
     refrained
    1.01
     avoidance
    0.97
     избе
    0.96
     refrain
    0.95
     Avoid
    0.93
     menghindari
    0.93
    Activations Density 0.003%

    No Known Activations