© 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. 29439
    Prev
    Next
    INDEX
    Explanations

    specific nouns and concepts

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

    Davies, Math, llama, Attempt

    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
     confers
    0.56
     میلیارد
    0.55
    ontiti
    0.52
    navigationLinks
    0.50
    勂
    0.50
     accommodate
    0.50
     كار
    0.47
     primaryLanguage
    0.46
     أبر
    0.45
     ヘア
    0.45
    POSITIVE LOGITS
    o
    0.51
    正月
    0.46
    ละ
    0.45
     इधर
    0.44
    น
    0.44
     site
    0.43
    인을
    0.43
    hesians
    0.43
    imation
    0.43
     пъ
    0.43
    Activations Density 0.000%

    No Known Activations