© 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. 46954
    Prev
    Next
    INDEX
    Explanations

    legal and technical terms

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

    factors, prime, Seller, layout

    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
    refour
    0.48
     –
    0.47
    ix
    0.46
    am
    0.46
    are
    0.46
    ipolar
    0.46
    amed
    0.45
    ized
    0.45
    ales
    0.44
    quality
    0.44
    POSITIVE LOGITS
     arqué
    0.52
    Gö
    0.49
    嵃
    0.49
    ᒎ
    0.49
     appliqué
    0.48
     confirmé
    0.47
    ﺨ
    0.47
     самостоятельно
    0.46
     regreso
    0.46
    πάν
    0.46
    Activations Density 0.000%

    No Known Activations