© 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. 160411
    Prev
    Next
    INDEX
    Explanations

    evaluating descriptions or specifications

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

    technical terms and commands

    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
    Panorama
    0.52
    ቆዳ
    0.49
     Panorama
    0.48
    Estimated
    0.48
    ሐ
    0.47
     paket
    0.46
     stroll
    0.46
     évent
    0.44
     जिन्हें
    0.44
     magnific
    0.44
    POSITIVE LOGITS
    యి
    0.47
    ys
    0.46
    ương
    0.44
    .},
    0.44
    ahue
    0.44
     одному
    0.43
     niego
    0.43
    isive
    0.43
    ())
    0.42
    elt
    0.42
    Activations Density 0.001%

    No Known Activations