© 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. 177876
    Prev
    Next
    INDEX
    Explanations

    property descriptions

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

    code, commands, and flags

    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
    Aunque
    0.48
    Branch
    0.47
    இ
    0.46
    Maar
    0.45
    Els
    0.45
    Toplam
    0.43
    ла
    0.43
     направления
    0.42
     услуги
    0.42
    Services
    0.41
    POSITIVE LOGITS
     classifier
    0.57
     rivest
    0.53
    ﻨ
    0.49
     simulator
    0.49
     leptonic
    0.48
     archaic
    0.47
     Nato
    0.47
     Jaipur
    0.47
     simulation
    0.46
     simulating
    0.46
    Activations Density 0.002%

    No Known Activations