© 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. 239644
    Prev
    Next
    INDEX
    Explanations

    child/ward, cleanse, learn, receive

    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
    蓖
    0.50
    supseteq
    0.48
     পিঁপড়া
    0.48
     นิ
    0.47
    }'.
    0.46
     кушымта
    0.46
    യിലേ
    0.46
    ều
    0.46
     然后
    0.45
    apadani
    0.45
    POSITIVE LOGITS
     runs
    0.48
     sweeps
    0.45
     WAV
    0.44
     decays
    0.41
     haces
    0.41
     Wagon
    0.40
    ʂ
    0.40
     euph
    0.40
     Putra
    0.40
     misses
    0.40
    Activations Density 0.002%

    No Known Activations