© 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. 126484
    Prev
    Next
    INDEX
    Explanations

    realms, editors, specifically

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

    technical and abstract concepts

    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
    spectrum
    0.52
    mute
    0.51
    n
    0.50
     کم
    0.50
     zbog
    0.49
    adb
    0.48
    成績
    0.47
    y
    0.46
    extension
    0.46
    r
    0.46
    POSITIVE LOGITS
    뮈
    0.49
    ोट
    0.49
     marginalized
    0.48
    льными
    0.47
    fZ
    0.47
    ཋ
    0.46
    зирован
    0.46
     polypeptide
    0.46
     veiled
    0.46
    вими
    0.45
    Activations Density 0.000%

    No Known Activations