© 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. 50418
    Prev
    Next
    INDEX
    Explanations

    buying pillows

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

    describes states or actions

    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
     prefque
    0.54
    доз
    0.54
    ahaman
    0.54
     hảo
    0.50
    ulang
    0.49
    ozen
    0.49
    osim
    0.48
    ϋ
    0.48
     可愛
    0.47
     カバー
    0.47
    POSITIVE LOGITS
     Telegraph
    0.48
    Printer
    0.46
     Pops
    0.44
     Glock
    0.43
     engine
    0.43
     Zodiac
    0.42
     Miranda
    0.42
    Independence
    0.42
     Archaeological
    0.41
    ется
    0.41
    Activations Density 0.000%

    No Known Activations