© 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. 89037
    Prev
    Next
    INDEX
    Explanations

    end of service

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

    booking search aws os decl

    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
     Oktober
    0.55
     kapat
    0.55
     Ú
    0.54
     October
    0.53
     Latino
    0.51
     din
    0.49
     lave
    0.49
     konkre
    0.49
     黃
    0.49
     film
    0.49
    POSITIVE LOGITS
    Созда
    0.52
    DECL
    0.49
    ähler
    0.49
    тых
    0.47
    ujud
    0.47
    ərd
    0.47
    RESULT
    0.46
    Decl
    0.46
    সব
    0.46
    ουσ
    0.45
    Activations Density 0.000%

    No Known Activations