© 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. 124454
    Prev
    Next
    INDEX
    Explanations

    decrease

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

    voltage/cooling/paste followed by consequence

    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
    acles
    0.48
    etva
    0.45
    r
    0.42
    php
    0.41
    時から
    0.41
    :
    0.41
    acle
    0.40
    DEPARTMENT
    0.39
    csv
    0.39
    日時
    0.38
    POSITIVE LOGITS
     restaur
    0.54
     bigotry
    0.53
     Gabri
    0.52
     investi
    0.51
     encirc
    0.50
     Simón
    0.50
     円
    0.50
    स्पति
    0.50
     rescu
    0.49
     Anf
    0.49
    Activations Density 0.001%

    No Known Activations