© 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. 181438
    Prev
    Next
    INDEX
    Explanations

    loves children

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

    explaining item characteristics

    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
    anyak
    0.44
    ésie
    0.44
    arın
    0.43
    워서
    0.42
    ảm
    0.42
    基础
    0.42
    规定
    0.41
    <unused56>
    0.41
    abase
    0.41
    ंमुळे
    0.41
    POSITIVE LOGITS
     factual
    0.45
     regarding
    0.45
     Lorentzian
    0.44
    明確
    0.44
     характери
    0.43
     valign
    0.43
     similarity
    0.42
     continuant
    0.42
     convexe
    0.42
     definitive
    0.41
    Activations Density 0.000%

    No Known Activations