© 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. 79442
    Prev
    Next
    INDEX
    Explanations

    describes or annotates media

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

    swallow airspeed velocity

    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
    í
    0.52
    ú
    0.52
    ě
    0.47
    jí
    0.45
    ’
    0.45
    é
    0.45
    eted
    0.44
     tzv
    0.44
    不了
    0.44
    Í
    0.44
    POSITIVE LOGITS
     Editing
    0.54
     annotation
    0.49
     editing
    0.48
     exemplary
    0.47
     адміністра
    0.45
     Species
    0.45
    usermodel
    0.44
     école
    0.44
     Prisma
    0.44
     ANI
    0.44
    Activations Density 0.002%

    No Known Activations