© 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. 12262
    Prev
    Next
    INDEX
    Explanations

    recommendation and positive attributes

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

    reviews of places

    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
     pathogenesis
    0.44
     ως
    0.41
     etiology
    0.41
     perspici
    0.40
     implica
    0.40
    罹
    0.40
     theorists
    0.40
    ʹ
    0.39
     determinante
    0.39
     énon
    0.39
    POSITIVE LOGITS
    hotel
    0.48
     mooi
    0.48
     mooie
    0.47
     bagus
    0.47
    近く
    0.46
     desayuno
    0.46
     hotel
    0.46
     Excellent
    0.45
     đẹp
    0.45
     خوب
    0.45
    Activations Density 0.022%

    No Known Activations