© 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. 31755
    Prev
    Next
    INDEX
    Explanations

    availability and listing information

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

    company, objective, expression

    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
     показывать
    0.50
     triglycer
    0.46
     '|
    0.46
     determinate
    0.45
     QFile
    0.45
     clásica
    0.45
    ारात
    0.44
    .>
    0.44
    汨
    0.44
     revistas
    0.43
    POSITIVE LOGITS
    appropri
    0.50
     편성
    0.48
     항목
    0.48
    ANDER
    0.46
    кор
    0.44
    Hydrochloride
    0.44
    LEMENT
    0.44
    APPROVAL
    0.44
    HEY
    0.44
    Absorption
    0.43
    Activations Density 0.001%

    No Known Activations