© 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. 53281
    Prev
    Next
    INDEX
    Explanations

    negligent personalised procuring specializes

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

    very active

    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
    ULU
    0.53
    ΟΣ
    0.52
    Deutsch
    0.51
    ATUM
    0.51
    '$,
    0.50
    כות
    0.50
     womenProduct
    0.49
    ℚ
    0.49
    מות
    0.48
    QCD
    0.48
    POSITIVE LOGITS
     sear
    0.50
     escort
    0.47
    傾
    0.46
     James
    0.46
     Sabbath
    0.45
     nailed
    0.44
     Removes
    0.44
     creep
    0.44
     Hatch
    0.43
     Pau
    0.43
    Activations Density 0.001%

    No Known Activations