© 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. 99057
    Prev
    Next
    INDEX
    Explanations

    explicit endorsement

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

    specific dates or definitions

    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
     fonctionnalité
    0.54
     restroom
    0.52
     x
    0.51
     вход
    0.50
     orbitals
    0.49
     branchNode
    0.49
    𝔦
    0.49
     capacidad
    0.47
     tortilla
    0.47
     नोटबुक
    0.47
    POSITIVE LOGITS
    DB
    0.45
    Greg
    0.45
    admin
    0.45
    耆
    0.45
    taus
    0.44
    sudo
    0.43
    BB
    0.43
    经常
    0.43
    分析
    0.43
    goods
    0.43
    Activations Density 0.000%

    No Known Activations