© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 23662
    Prev
    Next
    INDEX
    Explanations

    describing subsequent context

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

    softened, accessible, prevented

    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
     lié
    0.26
     offres
    0.26
     vores
    0.26
     usos
    0.25
     demandes
    0.25
    قطه
    0.24
     uproar
    0.24
    ஷ
    0.24
    ಿ
    0.23
    ログイン
    0.23
    POSITIVE LOGITS
     корпора
    0.24
     অত্যন্ত
    0.23
     ICU
    0.23
     movingRect
    0.23
     গবেষণা
    0.22
     Potomac
    0.22
     Merrill
    0.22
     হীর
    0.22
    ocytes
    0.22
     সম্ভবত
    0.22
    Activations Density 0.162%

    No Known Activations