© 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. 5104
    Prev
    Next
    INDEX
    Explanations

    gorge yourself, transact under, sharing of

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

    when during input

    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
    ༡
    0.47
    ด
    0.46
     לי
    0.45
    ЕР
    0.45
    ซ
    0.44
    ラブ
    0.43
    Vamos
    0.42
    杰
    0.42
    לי
    0.42
    ร
    0.42
    POSITIVE LOGITS
     waarbij
    0.44
     causing
    0.39
     inade
    0.38
     allowable
    0.38
     of
    0.38
     wildflower
    0.38
     when
    0.37
     resulting
    0.37
     during
    0.37
     When
    0.37
    Activations Density 0.010%

    No Known Activations