© 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. 106068
    Prev
    Next
    INDEX
    Explanations

    system islong absenceRemember the

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

    part, tasks, sections

    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
     antennis
    0.54
    tien
    0.47
     confertim
    0.45
    組み
    0.44
    علی
    0.43
     próp
    0.42
    setConfig
    0.42
    ۰
    0.42
     alakalı
    0.41
     propi
    0.41
    POSITIVE LOGITS
     became
    0.50
    af
    0.49
     longest
    0.49
     points
    0.48
     konnte
    0.46
     Kashmir
    0.46
    പ്
    0.46
    一点
    0.45
    一點
    0.45
    utis
    0.45
    Activations Density 0.000%

    No Known Activations