© 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. 74003
    Prev
    Next
    INDEX
    Explanations

    photographic essay

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

    physical devices, high growth, dynamic imports

    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
    处于
    0.52
    рон
    0.49
    朮
    0.48
    АЗ
    0.47
    较
    0.47
    త్మ
    0.46
    جل
    0.46
    гляд
    0.46
    ంక
    0.46
    వర్
    0.46
    POSITIVE LOGITS
    f
    0.50
     ανθρώ
    0.47
    crab
    0.45
    cof
    0.44
    bathtub
    0.43
    crs
    0.43
     estrogen
    0.42
     coi
    0.42
     cambiamento
    0.42
     Nicole
    0.42
    Activations Density 0.000%

    No Known Activations