© 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. 135351
    Prev
    Next
    INDEX
    Explanations

    life and ships

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

    links, processes, products, properties

    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
    0.55
    ↵↵
    0.48
     censure
    0.45
    ed
    0.44
     to
    0.42
    apolis
    0.42
    $
    0.42
    oster
    0.41
    Hooks
    0.41
    Links
    0.41
    POSITIVE LOGITS
    поряд
    0.64
     వివర
    0.55
    焔
    0.53
     personales
    0.52
     wynik
    0.52
     уровень
    0.51
    पयोग
    0.51
    𒊕
    0.51
     niveaux
    0.50
     níveis
    0.50
    Activations Density 0.001%

    No Known Activations