© 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. 208823
    Prev
    Next
    INDEX
    Explanations

    innovative technologies around

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

    key messaging and budget summaries

    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
     qīng
    0.46
     চীন
    0.44
    🎆
    0.44
     চীনের
    0.44
     "????
    0.43
    âtel
    0.42
    গায়
    0.41
     superfície
    0.41
     σύμφωνα
    0.41
     તમે
    0.41
    POSITIVE LOGITS
     모
    0.48
    ied
    0.44
    ays
    0.44
    l
    0.44
    isation
    0.44
    ibs
    0.43
    amatan
    0.43
     customary
    0.42
    च
    0.41
    हल
    0.41
    Activations Density 0.000%

    No Known Activations