© 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. 189712
    Prev
    Next
    INDEX
    Explanations

    observes that probably

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

    budget and effort

    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
     طيب
    0.44
    ifications
    0.43
     النا
    0.42
    ža
    0.42
     않고
    0.39
     கொ
    0.39
    {,}
    0.39
    Admission
    0.39
     ত
    0.38
     powin
    0.38
    POSITIVE LOGITS
    ोटेन
    0.54
     পুরোপুরি
    0.51
     formie
    0.50
    молу
    0.49
    केमॉन
    0.48
     Demonstrated
    0.47
     форме
    0.46
    село
    0.46
    र्मेंद्र
    0.46
    াউন
    0.46
    Activations Density 0.002%

    No Known Activations