© 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. 121505
    Prev
    Next
    INDEX
    Explanations

    image processing, remediation, software, pool, home, price, waterproofing

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

    deflation or compression

    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
    8
    0.44
     ид
    0.40
     their
    0.40
    9
    0.39
     transmit
    0.37
     interpolate
    0.37
    7
    0.37
     leurs
    0.37
     wiss
    0.37
     prosecute
    0.36
    POSITIVE LOGITS
     ถ้า
    0.54
     했는데
    0.48
     جایی
    0.46
     แต่
    0.46
     وقتی
    0.46
    auteur
    0.45
     น้ำ
    0.44
     אבל
    0.44
    ◔
    0.44
    牷
    0.44
    Activations Density 0.000%

    No Known Activations