© 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. 115435
    Prev
    Next
    INDEX
    Explanations

    company, retain, to, New

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

    Access Management and Requirements

    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
    忓
    0.51
    ه
    0.49
     ناج
    0.47
    ك
    0.46
     ری
    0.46
    装修
    0.46
     تدخل
    0.46
    𝚊
    0.45
     recebe
    0.44
     સફળ
    0.44
    POSITIVE LOGITS
    iosis
    0.54
     Anticip
    0.54
     Motorcycle
    0.49
    IAS
    0.49
     Strict
    0.48
    ታት
    0.48
     Incidentally
    0.48
    idoo
    0.48
     Physiological
    0.48
     Patient
    0.47
    Activations Density 0.000%

    No Known Activations