© 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. 19759
    Prev
    Next
    INDEX
    Explanations

    collocations and common phrases

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

    english, Dek, Hammer, effect, oxygen

    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
    ictus
    0.48
    attacks
    0.46
    enterprise
    0.46
    उ
    0.45
    houses
    0.45
    intah
    0.45
     tuck
    0.45
    kim
    0.45
     dérou
    0.45
    agenda
    0.45
    POSITIVE LOGITS
     συνεχ
    0.51
     kürz
    0.46
    (&(
    0.46
     minim
    0.45
    ‌,
    0.44
    ‌కు
    0.44
     เก
    0.44
    繽
    0.44
    जूदा
    0.43
    :...
    0.43
    Activations Density 0.000%

    No Known Activations