© 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. 109902
    Prev
    Next
    INDEX
    Explanations

    descriptions and states of being

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

    women and conditions

    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
    のない
    0.48
     erstes
    0.47
     pierwszym
    0.46
     erste
    0.46
     gomme
    0.45
    、《
    0.45
    월
    0.45
    私募
    0.44
     первом
    0.43
     przeci
    0.43
    POSITIVE LOGITS
    <h3>
    0.48
    <h4>
    0.48
     ·
    0.46
    ώρα
    0.43
     наста
    0.42
    <h6>
    0.41
    ে
    0.41
    i
    0.41
    ină
    0.40
    inato
    0.40
    Activations Density 0.001%

    No Known Activations