© 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. 209998
    Prev
    Next
    INDEX
    Explanations

    language and context

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

    explaining and understanding specific code

    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
    et
    0.56
    Event
    0.54
     啊
    0.54
    斷
    0.54
    N
    0.53
    Personal
    0.52
    Shared
    0.50
    q
    0.49
    ver
    0.49
    രാ
    0.49
    POSITIVE LOGITS
    াচার
    0.53
     одну
    0.47
    единен
    0.47
     окра
    0.46
    ЕНИ
    0.46
     tất
    0.46
     tyres
    0.45
    を目
    0.45
    ार्‍या
    0.44
     equates
    0.44
    Activations Density 0.000%

    No Known Activations