© 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. 212904
    Prev
    Next
    INDEX
    Explanations

    rights and terms

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

    code, code, code

    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
    ówki
    0.52
     decyz
    0.49
    체의
    0.48
    Déc
    0.48
    yCoordinate
    0.47
    گیز
    0.47
    현
    0.47
    bí
    0.47
    ział
    0.46
    kum
    0.46
    POSITIVE LOGITS
     checklist
    0.48
     पहुंच
    0.46
     दिनेश
    0.45
     Checklist
    0.45
     सुबह
    0.44
     TCP
    0.44
     sbParams
    0.44
     woken
    0.44
     Been
    0.43
     увиде
    0.43
    Activations Density 0.002%

    No Known Activations