© 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. 27500
    Prev
    Next
    INDEX
    Explanations

    making a field

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

    building digital worlds

    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
    ノ
    0.50
     замени
    0.47
    ajjati
    0.47
    েনার
    0.45
     izay
    0.45
    вила
    0.44
    ඓ
    0.44
    Noah
    0.43
     unforgettable
    0.42
    ан
    0.42
    POSITIVE LOGITS
    /
    0.47
     infring
    0.45
     geschaffen
    0.45
     conness
    0.45
     registrations
    0.45
     portfolios
    0.44
     acolo
    0.44
     allong
    0.44
    ப்படுகின்றன
    0.44
     liabilities
    0.44
    Activations Density 0.000%

    No Known Activations