© 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. 208955
    Prev
    Next
    INDEX
    Explanations

    which was announced

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

    new and immediate effect

    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
    磪
    0.49
     estet
    0.47
     দর্শন
    0.46
     Plugin
    0.46
     قرارداد
    0.46
    EventHandler
    0.45
     errorHandler
    0.45
     इवेंट
    0.45
     Iterator
    0.45
     기념
    0.45
    POSITIVE LOGITS
     manifestly
    0.45
    pathetic
    0.45
    毅
    0.44
     Fam
    0.44
    fam
    0.43
     κάνει
    0.42
    ALTH
    0.42
     loving
    0.41
    Β
    0.41
    如果您
    0.41
    Activations Density 0.000%

    No Known Activations