© 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. 197102
    Prev
    Next
    INDEX
    Explanations

    descriptions following colons

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

    describing photograph contents

    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
     tế
    0.53
     क्वांट
    0.48
     दौड़
    0.46
    श्व
    0.45
     ее
    0.44
     Gambit
    0.44
    歆
    0.44
     बै
    0.43
    णाऱ्या
    0.43
     sprinting
    0.43
    POSITIVE LOGITS
    ylmethylsulfanyl
    0.51
    unicode
    0.50
    んにちは
    0.48
    duc
    0.45
     yksi
    0.45
    ;
    0.45
     buscas
    0.44
    ten
    0.44
     suelo
    0.44
    element
    0.44
    Activations Density 0.001%

    No Known Activations