© 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. 3669
    Prev
    Next
    INDEX
    Explanations

    legal or technical phrases

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

    assertion statement, coming soon, dangers involved, minimal locale

    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
     মূল
    0.29
     photoshoot
    0.28
     tablespoons
    0.26
    ିକ
    0.26
     ছবি
    0.26
     raffle
    0.26
     hydrating
    0.26
    ক
    0.26
     মাছ
    0.25
    蓝牙
    0.25
    POSITIVE LOGITS
     engender
    0.30
     ungew
    0.30
     Tento
    0.29
     neurotic
    0.29
     Alguns
    0.28
     apud
    0.28
     Tade
    0.28
     perdu
    0.27
     conceito
    0.27
     considéré
    0.26
    Activations Density 0.249%

    No Known Activations