© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 13912
    Prev
    Next
    INDEX
    Explanations

    c# using System;

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    equals
    0.41
    اوار
    0.40
    до
    0.40
    дык
    0.39
    бре
    0.38
    荇
    0.38
     ಇದರ
    0.37
     كلهم
    0.37
    memory
    0.36
     bě
    0.36
    POSITIVE LOGITS
    ;
    0.52
    ;
    0.44
    ؛
    0.43
    ();
    0.39
     conceivable
    0.39
     దర్శ
    0.38
    ಚ್
    0.38
    ;")
    0.38
     grabs
    0.37
    ;|
    0.37
    Activations Density 0.001%

    No Known Activations