© 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. 142167
    Prev
    Next
    INDEX
    Explanations

    words of wisdom

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

    actual APIs Certificates Data care

    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
    াক
    0.49
     Repubblica
    0.48
     McDaniel
    0.47
     Harald
    0.47
     Daniela
    0.47
    럽
    0.46
    笠
    0.46
    সভাপতি
    0.45
    Storia
    0.45
    ка
    0.45
    POSITIVE LOGITS
    lane
    0.54
    omen
    0.51
     गोल्ड
    0.49
    propagation
    0.49
     invigorating
    0.49
     ऊ
    0.48
    gold
    0.48
     तेज
    0.48
    frying
    0.47
    times
    0.47
    Activations Density 0.000%

    No Known Activations