© 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. 219946
    Prev
    Next
    INDEX
    Explanations

    comparisons and measurements

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

    secret surveillance activities

    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
     nantinya
    0.46
    gem
    0.45
    廻
    0.44
    评
    0.44
    ミング
    0.43
    คุณ
    0.42
    گ
    0.41
    갑
    0.41
    polynomial
    0.41
    โค
    0.41
    POSITIVE LOGITS
    rische
    0.52
    óry
    0.47
    وجه
    0.46
     Eur
    0.46
     persiste
    0.45
     Ulrich
    0.45
    什麼
    0.44
     velké
    0.43
    ihe
    0.43
    rainer
    0.42
    Activations Density 0.000%

    No Known Activations