© 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. 11313
    Prev
    Next
    INDEX
    Explanations

    injection treatments

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

    listing components 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
    о
    0.43
    <0x80>
    0.38
    ва
    0.38
     үч
    0.36
     importantly
    0.35
    તો
    0.35
     Ն
    0.34
     একটি
    0.34
    트는
    0.33
    ཋ
    0.33
    POSITIVE LOGITS
     مرحبا
    0.39
     و
    0.39
     governorship
    0.37
     gospel
    0.37
     والن
    0.36
    چال
    0.36
     यानी
    0.36
    tywn
    0.35
     musicale
    0.35
     आणि
    0.34
    Activations Density 0.025%

    No Known Activations