© 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. 220346
    Prev
    Next
    INDEX
    Explanations

    paid for parking

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

    power and control

    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
    惻
    0.52
    淩
    0.49
    譏
    0.48
    ستم
    0.46
    Прави
    0.46
    undet
    0.46
    瞟
    0.46
     분명
    0.45
    ४
    0.45
    Dest
    0.45
    POSITIVE LOGITS
     tsy
    0.44
     internacionales
    0.43
     negligent
    0.43
     upscale
    0.43
     Empire
    0.42
    appendTo
    0.42
     tourisme
    0.42
     także
    0.41
     xwe
    0.41
     empire
    0.41
    Activations Density 0.001%

    No Known Activations