© 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. 137383
    Prev
    Next
    INDEX
    Explanations

    understand these risks

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

    arrest, call, day, reveals

    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
     rivets
    0.54
     Букмекерлар
    0.52
     canales
    0.51
    ק
    0.49
    Го
    0.48
     cathodes
    0.48
     канал
    0.48
    มัน
    0.46
     functors
    0.46
    ס
    0.46
    POSITIVE LOGITS
    n
    0.53
    ong
    0.50
    ach
    0.49
    tableau
    0.46
    ot
    0.45
    tall
    0.45
    undert
    0.44
     Securities
    0.43
    ut
    0.43
    ci
    0.43
    Activations Density 0.000%

    No Known Activations