© 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. 188893
    Prev
    Next
    INDEX
    Explanations

    stall bedtimesenior year

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

    language representation

    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
    δικ
    0.46
    스트
    0.41
    一身
    0.40
    \}
    0.39
    绮
    0.39
    原
    0.39
    隶
    0.39
    پس
    0.39
     సరి
    0.39
    Dollars
    0.39
    POSITIVE LOGITS
     করছি
    0.62
     効果
    0.52
     theyre
    0.51
     وما
    0.50
     tabpos
    0.49
     чаще
    0.48
     холоди
    0.48
     وبا
    0.48
     вижу
    0.47
     他们
    0.47
    Activations Density 0.001%

    No Known Activations