© 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. 200154
    Prev
    Next
    INDEX
    Explanations

    doors, reading materials, stone, separate, numbers, right, weekly, on, and

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

    comfortable, access, future, soon

    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
    écart
    0.56
     பாபிலோ
    0.55
     Résultats
    0.54
     Результа
    0.52
    Результа
    0.52
    茆
    0.51
     применения
    0.50
    JSX
    0.50
    BufOffset
    0.50
    Эк
    0.50
    POSITIVE LOGITS
     rubber
    0.46
     cannot
    0.45
     hotels
    0.44
     can
    0.42
    로는
    0.42
     cancellation
    0.42
    로
    0.41
    ater
    0.41
     businessmen
    0.41
     hotel
    0.41
    Activations Density 0.002%

    No Known Activations