© 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. 33487
    Prev
    Next
    INDEX
    Explanations

    is required

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

    ready for

    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
     salaries
    0.54
     redonde
    0.50
     vests
    0.48
     errado
    0.47
     subgroups
    0.46
     égal
    0.46
     metabolites
    0.46
    Ꮡ
    0.46
     appartenant
    0.46
     spacers
    0.45
    POSITIVE LOGITS
    Sim
    0.54
    access
    0.52
    acknow
    0.51
    web
    0.49
    acknowled
    0.49
    jezd
    0.49
    acknowledge
    0.48
    sim
    0.48
    Action
    0.48
    Draw
    0.48
    Activations Density 0.000%

    No Known Activations