© 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. 126124
    Prev
    Next
    INDEX
    Explanations

    prospective visitors, wanted, goods, signed

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

    generating or delivering elements

    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
    ف
    0.63
    بر
    0.59
    R
    0.54
    Ils
    0.52
    an
    0.48
    f
    0.47
    闖
    0.47
    hlas
    0.46
    kopf
    0.45
    ι
    0.45
    POSITIVE LOGITS
    致します
    0.50
     dimers
    0.50
     insuf
    0.49
     beads
    0.48
     kosong
    0.48
     boxes
    0.47
     आती
    0.47
     couplers
    0.47
     cabin
    0.46
     rows
    0.46
    Activations Density 0.000%

    No Known Activations