© 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. 196024
    Prev
    Next
    INDEX
    Explanations

    news release headers

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

    next-best-action

    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
     chatbot
    0.49
     videocon
    0.48
    ⁹
    0.46
     chain
    0.46
     polarization
    0.46
     chat
    0.46
     hadron
    0.46
    espresso
    0.45
     renewed
    0.44
     congregate
    0.44
    POSITIVE LOGITS
     hilfreich
    0.49
    เรียน
    0.48
     сложных
    0.43
     Tages
    0.43
    용
    0.43
    容
    0.42
     புரிய
    0.41
     увлека
    0.41
     сообщает
    0.41
    町村
    0.41
    Activations Density 0.000%

    No Known Activations