© 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. 23741
    Prev
    Next
    INDEX
    Explanations

    giveaway contest chance

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

    action to | accounts for | navigating a | ventures into

    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
     defy
    0.54
    ኮ
    0.47
    Bib
    0.46
    BIB
    0.45
     realizzazione
    0.45
     bib
    0.44
     అవ
    0.43
    figer
    0.43
     stayed
    0.43
     rig
    0.43
    POSITIVE LOGITS
    崞
    0.45
    ⇐
    0.45
     Partai
    0.45
    tStart
    0.44
     قسمت
    0.44
    ʏ
    0.43
    ylül
    0.43
    今後の
    0.43
    大型
    0.42
     その他
    0.42
    Activations Density 0.000%

    No Known Activations