© 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. 116911
    Prev
    Next
    INDEX
    Explanations

    geographically located words

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

    pieces have greater mobility

    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
    <td>
    0.53
     zigzag
    0.47
     disassembly
    0.46
     የማይ
    0.46
     নিজেকে
    0.44
     Blackjack
    0.44
     Into
    0.43
    ීය
    0.43
     আগে
    0.42
     wavefunction
    0.42
    POSITIVE LOGITS
    ller
    0.52
    lepas
    0.52
    λα
    0.47
     THESE
    0.46
    글
    0.45
    뭍
    0.45
    땅
    0.44
    tter
    0.44
    레
    0.44
    getCustomer
    0.44
    Activations Density 0.001%

    No Known Activations