© 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. 90090
    Prev
    Next
    INDEX
    Explanations

    projects, sick animal, study your, Pro, oxygen, too, drug

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

    capital of

    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
    Restaurant
    0.46
    Dancing
    0.43
    A
    0.43
     सर्वोच्च
    0.43
    Secrets
    0.39
    Referring
    0.39
    τικ
    0.39
     theses
    0.39
    TIA
    0.38
     restaur
    0.38
    POSITIVE LOGITS
    pping
    0.54
    brano
    0.51
    porcion
    0.51
    ood
    0.48
    ₂,
    0.48
     líqu
    0.47
     формы
    0.47
    पीठ
    0.47
    encing
    0.46
    fiere
    0.46
    Activations Density 0.002%

    No Known Activations