© 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. 155374
    Prev
    Next
    INDEX
    Explanations

    travel game guide

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

    dataset description overview

    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
     ƒ
    0.49
     svo
    0.48
     sám
    0.45
     jähr
    0.44
     hấp
    0.44
     ‚
    0.43
     tiges
    0.43
     '*')
    0.42
     yeri
    0.42
     Evet
    0.42
    POSITIVE LOGITS
    これ
    0.54
    それ
    0.50
    Birthday
    0.49
    که
    0.49
    birthday
    0.48
    ３
    0.48
    Pok
    0.48
    นั้น
    0.48
    신
    0.47
    that
    0.47
    Activations Density 0.000%

    No Known Activations