© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 172101
    Prev
    Next
    INDEX
    Explanations

    condition, mommy, heals, off, pert, constitution, extremist

    np_acts-logits-general · gemini-2.5-flash-lite

    crisis and consolidation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ADO
    0.57
    ado
    0.53
     المعلومات
    0.47
    ۹
    0.46
    icism
    0.46
     Marl
    0.46
     leggi
    0.46
    ATION
    0.45
    ༣
    0.45
    WR
    0.45
    POSITIVE LOGITS
     midline
    0.46
    気の
    0.44
     sacrificio
    0.44
    。
    0.43
    后
    0.43
     purely
    0.42
     religiously
    0.41
     bulb
    0.40
    向き
    0.40
     politically
    0.40
    Activations Density 0.001%

    No Known Activations