© 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. 3537
    Prev
    Next
    INDEX
    Explanations

    future proof

    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
     daugiau
    1.36
     karenge
    1.32
     dolgo
    1.30
     выпуск
    1.29
     меньше
    1.28
    `);
    1.27
     espera
    1.27
    اك
    1.26
     میلیون
    1.26
     kolejne
    1.25
    POSITIVE LOGITS
    etting
    1.42
    ures
    1.28
     Alman
    1.24
    atures
    1.22
    ests
    1.21
    ⇑
    1.19
    eding
    1.18
    checklist
    1.16
    italic
    1.16
    its
    1.16
    Activations Density 0.020%

    No Known Activations