© 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. 3939
    Prev
    Next
    INDEX
    Explanations

    transitions like but after or ends as

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

    Okonomiyaki and Takoyaki

    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
     fanáticos
    0.46
    耇
    0.44
     Irlanda
    0.44
     nhá
    0.44
    ターゲット
    0.42
    遺跡
    0.42
    כ
    0.42
    筊
    0.42
    בח
    0.42
     இதுபோன்ற
    0.42
    POSITIVE LOGITS
    fmt
    0.44
     creates
    0.43
    most
    0.41
    ​​​​
    0.39
    embar
    0.39
    بيوتر
    0.39
    await
    0.38
     added
    0.38
     variously
    0.38
     oi
    0.38
    Activations Density 0.000%

    No Known Activations