© 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. 84738
    Prev
    Next
    INDEX
    Explanations

    augmented reality technology

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

    original documents and origins

    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
    극
    0.49
     Premium
    0.46
    무
    0.46
    frac
    0.46
    모
    0.45
     ११
    0.45
    펨
    0.44
    노
    0.44
    덜
    0.44
    ツ
    0.44
    POSITIVE LOGITS
     Königs
    0.45
     übertr
    0.44
    děpodob
    0.44
    kaisi
    0.44
    ंसू
    0.43
    abhuto
    0.42
     diperlukan
    0.42
    determining
    0.42
     এনে
    0.41
    تين
    0.41
    Activations Density 0.000%

    No Known Activations