© 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. 37771
    Prev
    Next
    INDEX
    Explanations

    our product

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

    shopping cart and repository

    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
     exclusivement
    0.60
     exclusivamente
    0.59
     envers
    0.50
     xác
    0.50
     fréquemment
    0.48
     bò
    0.48
     sức
    0.48
    </h5>
    0.46
     một
    0.46
     exclusively
    0.45
    POSITIVE LOGITS
    iativa
    0.47
    ろう
    0.46
    Latch
    0.46
    daemon
    0.46
    tire
    0.45
    Pi
    0.45
    habitation
    0.45
    killing
    0.44
    drivers
    0.43
     demonstration
    0.43
    Activations Density 0.000%

    No Known Activations