© 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. 94889
    Prev
    Next
    INDEX
    Explanations

    . shaped

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

    you love unconditionally

    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
    中年
    0.49
    ωνα
    0.48
     Synth
    0.48
    典
    0.48
    োদিত
    0.47
     diaries
    0.43
    闰
    0.43
     flexibly
    0.42
    наче
    0.41
    耳
    0.41
    POSITIVE LOGITS
    ﻮ
    0.54
     svojoj
    0.49
     மில்லியன்
    0.49
     어느
    0.48
    उसके
    0.48
    ﻭ
    0.48
     പിന്നീട്
    0.48
    TE
    0.47
    ﺮ
    0.47
     p
    0.47
    Activations Density 0.000%

    No Known Activations