© 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. 191300
    Prev
    Next
    INDEX
    Explanations

    under no circumstances

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

    mechanisms that enable or follow

    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
    浯
    0.48
    ⚖
    0.46
    स्ता
    0.45
    atation
    0.44
     διαφορε
    0.43
    𒉺
    0.43
    第一個
    0.43
     creases
    0.42
    örungen
    0.42
    
    0.42
    POSITIVE LOGITS
     mannen
    0.55
     девушка
    0.53
     professora
    0.49
     directeur
    0.48
     tahu
    0.47
     memb
    0.46
     yem
    0.46
     gadis
    0.45
     +
    0.45
     directora
    0.45
    Activations Density 0.002%

    No Known Activations