© 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. 24116
    Prev
    Next
    INDEX
    Explanations

    financial planning and requirements

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

    instructions designed

    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
    lllll
    0.44
     olla
    0.41
    wijs
    0.41
     stessi
    0.40
    ില്‍
    0.40
    |</
    0.40
     Pokud
    0.40
    \|,
    0.40
     Oui
    0.39
    zioni
    0.39
    POSITIVE LOGITS
     снаб
    0.52
     silvery
    0.44
     невро
    0.43
    Responsive
    0.42
     multifaceted
    0.41
    кновен
    0.41
    escu
    0.40
    कोल
    0.40
    роид
    0.40
    ర్గ
    0.40
    Activations Density 0.000%

    No Known Activations