© 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. 180627
    Prev
    Next
    INDEX
    Explanations

    finance and serious deterioration

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

    finding or measuring

    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
    烪
    0.48
    だけの
    0.47
     অপূর্ব
    0.46
     craindre
    0.46
     ポイント
    0.46
     俺
    0.45
     すご
    0.45
     Linkedin
    0.45
     révèle
    0.45
     関
    0.45
    POSITIVE LOGITS
    usu
    0.57
    akukan
    0.48
    the
    0.47
    irst
    0.46
    ඡ
    0.46
    ʻ
    0.44
    wechsel
    0.44
    mutate
    0.44
    ंना
    0.43
    Siehe
    0.43
    Activations Density 0.001%

    No Known Activations