© 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. 9566
    Prev
    Next
    INDEX
    Explanations

    going back

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

    backwards or undo

    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
     concordance
    0.41
    paired
    0.40
     trivalent
    0.39
    ంద్ర
    0.38
    そのまま
    0.37
     نقل
    0.37
     पहना
    0.37
    <0x93>
    0.36
    gnet
    0.36
    aceae
    0.35
    POSITIVE LOGITS
     backtrack
    1.08
     backtracking
    1.05
    回头
    1.05
     назад
    0.96
     reversed
    0.93
     indietro
    0.93
     zurück
    0.89
     backwards
    0.88
     reversing
    0.88
     revenir
    0.88
    Activations Density 0.056%

    No Known Activations