© 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. 32388
    Prev
    Next
    INDEX
    Explanations

    dates and locations

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

    exits, automatically, product, geometric, typo, idiom, brick

    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
    後半
    0.44
     soorten
    0.40
    被害
    0.38
    看護
    0.38
    大きい
    0.38
    форми
    0.38
    温柔
    0.37
    ޞ
    0.37
    図
    0.37
    罠
    0.37
    POSITIVE LOGITS
    गृह
    0.44
     चैम्पियन
    0.43
    сюда
    0.42
    hire
    0.41
     apprentice
    0.40
    ದ
    0.39
     Tatha
    0.38
     Hayley
    0.38
     apprenticeship
    0.38
     Mascot
    0.38
    Activations Density 0.000%

    No Known Activations