© 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. 4482
    Prev
    Next
    INDEX
    Explanations

    contextual events

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

    defining concepts or topics

    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
     dessa
    0.52
     vardır
    0.51
     possiamo
    0.51
     we
    0.50
     (
    0.47
     dieser
    0.47
     tämä
    0.47
     nosso
    0.45
     podemos
    0.45
     Tämä
    0.45
    POSITIVE LOGITS
     amid
    0.70
    。
    0.59
     despite
    0.55
     지난해
    0.54
     رغم
    0.52
    despite
    0.51
    '.
    0.50
    ".
    0.49
    ។
    0.48
    ።
    0.48
    Activations Density 0.221%

    No Known Activations