© 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. 238845
    Prev
    Next
    INDEX
    Explanations

    free from, disaster committed, must have, control region

    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
     Urlaub
    0.53
     Treasures
    0.51
     Lockdown
    0.50
     Deux
    0.47
     Treasure
    0.45
     😍
    0.45
     pandemi
    0.45
     👀
    0.44
     [...
    0.44
     🙌
    0.43
    POSITIVE LOGITS
    ၷ
    0.52
    immt
    0.50
    ﻚ
    0.50
    ཥ
    0.50
    Ფ
    0.48
    숄
    0.47
    ﾑ
    0.47
    Solid
    0.46
    এছাড়া
    0.46
    isjon
    0.46
    Activations Density 0.000%

    No Known Activations