© 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. 17177
    Prev
    Next
    INDEX
    Explanations

    Mark portable other would around

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

    multi-lingual 'also' and json

    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
    どんどん
    0.48
    が良い
    0.48
    開店
    0.47
    いろいろ
    0.45
    手が
    0.45
     سبيل
    0.44
     സമയം
    0.43
    고
    0.42
     강력
    0.41
     congenial
    0.40
    POSITIVE LOGITS
    槑
    0.46
    也会
    0.45
    Also
    0.45
     aluno
    0.45
     Embed
    0.44
     Erlangen
    0.44
     Exper
    0.44
     også
    0.43
     théra
    0.43
     Bande
    0.43
    Activations Density 0.000%

    No Known Activations