© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3374
    Prev
    Next
    INDEX
    Explanations

    articles followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    詬
    1.25
    辕
    1.24
     consultas
    1.23
    轅
    1.23
    ناسب
    1.22
    inja
    1.21
     calendário
    1.21
    แนะนำ
    1.21
     önüne
    1.18
    </html>
    1.18
    POSITIVE LOGITS
    xffff
    1.40
     subtypes
    1.40
     Apol
    1.35
     zeta
    1.35
     multifamily
    1.31
     Eta
    1.30
     dext
    1.30
     Besitz
    1.28
     monomers
    1.28
     subtype
    1.28
    Activations Density 0.009%

    No Known Activations