© 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. 139705
    Prev
    Next
    INDEX
    Explanations

    multi-lingual text

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

    discussing yourself studies conversation pretends

    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
    ه
    0.61
     maest
    0.53
     defecto
    0.42
     totale
    0.41
     beneficio
    0.41
     abord
    0.41
     التط
    0.41
     contened
    0.40
     dimensione
    0.40
     الرح
    0.40
    POSITIVE LOGITS
     emphasised
    0.45
     virulent
    0.43
     wanna
    0.42
     prioritise
    0.42
     healer
    0.42
     血
    0.41
     virulence
    0.41
    ḵ
    0.41
     wording
    0.40
     weiterhin
    0.40
    Activations Density 0.002%

    No Known Activations