© 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. 74683
    Prev
    Next
    INDEX
    Explanations

    specialised equipment

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

    input() returns string

    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
    ुल
    0.50
    вые
    0.48
    Static
    0.46
    рама
    0.46
     बहाल
    0.44
    飾り
    0.44
    파
    0.44
    삼성
    0.43
     कोने
    0.43
    >
    0.43
    POSITIVE LOGITS
     poř
    0.50
     excel
    0.48
     další
    0.47
     organis
    0.47
     finanz
    0.47
     microorgan
    0.46
     beurre
    0.46
     pourcentage
    0.46
     pericolo
    0.46
     politique
    0.46
    Activations Density 0.000%

    No Known Activations