© 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. 165044
    Prev
    Next
    INDEX
    Explanations

    products and services

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

    minimizing or reducing quantity

    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
    іль
    0.49
    кові
    0.47
    ِد
    0.46
    Deleting
    0.45
    éna
    0.44
    Z
    0.44
    HARAD
    0.44
    ävä
    0.43
    ähler
    0.43
    Normalized
    0.43
    POSITIVE LOGITS
     exprim
    0.47
     surtout
    0.44
    買い物
    0.44
     вследствие
    0.44
     arousal
    0.44
     कैफ
    0.44
     olig
    0.43
     llor
    0.43
     ы
    0.42
     expres
    0.42
    Activations Density 0.000%

    No Known Activations