© 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. 19539
    Prev
    Next
    INDEX
    Explanations

    topmost, General, Managing

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

    dynamic, romantic, silent, cyclic

    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
    सादर
    0.54
     километ
    0.46
    presso
    0.46
    ूठी
    0.45
    ografía
    0.45
     blistering
    0.45
    cored
    0.45
    𝚓
    0.45
    ificar
    0.44
    方的
    0.44
    POSITIVE LOGITS
     truy
    0.46
     nào
    0.46
    ^{\
    0.45
     DID
    0.45
     оф
    0.45
     IN
    0.45
     BAS
    0.44
    ^{-
    0.44
     Offenders
    0.44
     manifest
    0.43
    Activations Density 0.000%

    No Known Activations