© 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. 73695
    Prev
    Next
    INDEX
    Explanations

    fields, local, first, key

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

    Lagrangian, grip, credit limit, biological age, beta

    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
     Unterstüt
    0.50
     Mueller
    0.45
     Three
    0.44
    +\
    0.42
     After
    0.42
     Shares
    0.42
     Mounting
    0.42
    <0xE3>
    0.41
     &
    0.41
     Experiment
    0.41
    POSITIVE LOGITS
    дент
    0.52
    س
    0.49
    سن
    0.47
    міну
    0.47
    Бар
    0.47
    Ссы
    0.46
     подход
    0.46
    determin
    0.45
     мечта
    0.45
    комен
    0.45
    Activations Density 0.004%

    No Known Activations