© 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. 209660
    Prev
    Next
    INDEX
    Explanations

    specific identifiers like names, codes, or files

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

    what role to play

    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
    ्रीन
    0.51
    𒁺
    0.50
     ತಯ
    0.45
    ્રી
    0.45
    નુ
    0.43
     તેણી
    0.43
    گران
    0.43
    óm
    0.43
     તેણીએ
    0.43
    роди
    0.43
    POSITIVE LOGITS
     Annot
    0.44
     coincides
    0.44
     exemplaire
    0.44
     합니다
    0.44
     meilleure
    0.42
    ,
    0.42
     masterpiece
    0.42
     notes
    0.42
     credentials
    0.42
    上来
    0.42
    Activations Density 0.001%

    No Known Activations