© 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. 88359
    Prev
    Next
    INDEX
    Explanations

    after decision or otherwise

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

    gaslighting, dehydration, refactoring, motivation, statement, management

    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
    䚰
    0.49
    τρα
    0.49
     реконструк
    0.49
     Colorful
    0.48
    alarını
    0.47
     পূর্বাভাস
    0.47
     både
    0.46
     περισσότε
    0.46
    tiin
    0.46
     colourful
    0.45
    POSITIVE LOGITS
    d
    0.49
     irrepar
    0.46
     strangled
    0.46
     prosecuted
    0.44
    Tatar
    0.44
    en
    0.42
    länder
    0.42
     kurz
    0.42
    r
    0.42
     stubbornly
    0.42
    Activations Density 0.000%

    No Known Activations