© 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. 35694
    Prev
    Next
    INDEX
    Explanations

    sipping warm shout

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

    ages and vulnerability

    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
     Improves
    0.42
    に入れる
    0.42
    Lato
    0.41
     INCLUDING
    0.40
     (!)
    0.39
    噸
    0.39
     Amendments
    0.39
    atay
    0.39
     الداخلية
    0.39
     Electroly
    0.38
    POSITIVE LOGITS
     vẫn
    0.46
     दमदार
    0.46
     senang
    0.44
     sesuatu
    0.44
     agile
    0.44
     ५
    0.43
    係る
    0.43
     oposición
    0.43
     motoring
    0.43
     sizeable
    0.42
    Activations Density 0.000%

    No Known Activations