© 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. 50291
    Prev
    Next
    INDEX
    Explanations

    greeting followed by noun

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

    food, specific places, gender

    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
    an
    0.48
    f
    0.48
    jan
    0.46
     গ্রামে
    0.44
    am
    0.43
    b
    0.43
    j
    0.43
    get
    0.42
    pos
    0.42
     What
    0.42
    POSITIVE LOGITS
    ২০
    0.61
    Фото
    0.57
    উপ
    0.53
    檳
    0.52
    Ắ
    0.49
    Imidazole
    0.47
    Чер
    0.46
    Сере
    0.46
    ắc
    0.46
     Fortaleza
    0.45
    Activations Density 0.000%

    No Known Activations