© 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. 201365
    Prev
    Next
    INDEX
    Explanations

    whitish specks

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

    AI's limitations and feelings

    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
     sogar
    0.46
     μπορού
    0.46
     навіть
    0.45
    Mask
    0.45
    掩
    0.45
    MASK
    0.44
    okkh
    0.44
     даже
    0.44
    𝑪
    0.44
     gacche
    0.44
    POSITIVE LOGITS
     officially
    0.48
     DNS
    0.48
     branding
    0.46
     patented
    0.46
     ammonia
    0.45
     Payroll
    0.45
     mailing
    0.45
     Scientology
    0.45
     Hepatitis
    0.44
     exclusionary
    0.44
    Activations Density 0.001%

    No Known Activations