© 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. 127995
    Prev
    Next
    INDEX
    Explanations

    copyright notices

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

    phrases connecting concepts

    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
    ૯
    0.63
    ából
    0.53
    фель
    0.51
     женой
    0.50
     имат
    0.48
     அனுமதி
    0.48
     afferma
    0.47
    榱
    0.47
     строк
    0.47
    ۹
    0.46
    POSITIVE LOGITS
     pulses
    0.52
     minis
    0.48
    je
    0.47
     spirals
    0.47
     cologne
    0.46
     t
    0.46
     diesel
    0.46
     subtle
    0.45
     realtime
    0.45
     turning
    0.44
    Activations Density 0.001%

    No Known Activations