© 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. 13601
    Prev
    Next
    INDEX
    Explanations

    how to instructions

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

    questions about why or things

    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
     adenosine
    0.42
     nanofibers
    0.41
     biofilms
    0.40
     রকমের
    0.37
     determinadas
    0.37
    #-
    0.37
     cAMP
    0.37
     microbial
    0.36
     assays
    0.36
     cellulose
    0.35
    POSITIVE LOGITS
    𝔯
    0.45
     سید
    0.42
     venge
    0.42
    คองโก
    0.42
     Tiktok
    0.42
     murió
    0.41
     Funeral
    0.41
     सध्या
    0.40
     वंदे
    0.40
     Discord
    0.40
    Activations Density 0.013%

    No Known Activations