© 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. 29180
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units

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

    past events and history

    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
     trycatch
    0.46
    ORTYPE
    0.46
    顎
    0.44
     atthakath
    0.44
     ignoreString
    0.44
     andRow
    0.44
     شکل
    0.43
    aVal
    0.43
     newVal
    0.43
    う
    0.43
    POSITIVE LOGITS
    s
    0.52
    netz
    0.49
    youtube
    0.49
     speeches
    0.48
     preached
    0.48
    earnings
    0.48
     accomplishments
    0.47
     commercials
    0.47
     specimens
    0.47
    g
    0.46
    Activations Density 0.000%

    No Known Activations