© 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. 220254
    Prev
    Next
    INDEX
    Explanations

    those oversized items

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

    using services or methods

    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
    ↵
    0.53
     Cardiac
    0.52
    xi
    0.51
    >$
    0.51
     k
    0.50
    up
    0.49
     Microbial
    0.48
     (
    0.47
    ges
    0.47
     cardiac
    0.47
    POSITIVE LOGITS
     متش
    0.52
     trzech
    0.50
     metody
    0.50
     gême
    0.50
    ⊰
    0.49
     três
    0.48
     entspre
    0.47
    ༄
    0.45
    Questa
    0.45
    اری
    0.44
    Activations Density 0.001%

    No Known Activations