© 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. 240165
    Prev
    Next
    INDEX
    Explanations

    mirror, tablet, you, millions, administration

    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
    प्ट
    0.56
     જન્મ
    0.53
     अभिभाव
    0.50
     जन्
    0.48
     ब्याज
    0.48
    ValMap
    0.48
    謢
    0.47
    in
    0.46
     પ્રેમ
    0.46
     महाराज
    0.46
    POSITIVE LOGITS
     AMP
    0.48
     bmp
    0.46
     commencing
    0.45
    اضره
    0.45
    嘍
    0.45
    йте
    0.44
    сад
    0.44
     fft
    0.43
     nyc
    0.43
     empty
    0.42
    Activations Density 0.006%

    No Known Activations