© 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. 179362
    Prev
    Next
    INDEX
    Explanations

    sharing, similar, early, technician

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

    mind

    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
     अज्ञात
    0.48
    嶄
    0.47
     Cross
    0.46
     पप्पू
    0.44
     этими
    0.44
    Cross
    0.43
    '
    0.43
    🤴
    0.43
     ਰਹ
    0.42
    ಗಳಿಂದ
    0.42
    POSITIVE LOGITS
    t
    0.47
     vina
    0.45
     mape
    0.44
    lcc
    0.43
     düzey
    0.43
    lL
    0.43
     수준
    0.43
     medications
    0.42
     communic
    0.42
     isp
    0.42
    Activations Density 0.001%

    No Known Activations