© 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. 125504
    Prev
    Next
    INDEX
    Explanations

    possibilities, drinks, accommodations, student

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

    themes to avoid

    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
     Ihrem
    0.49
    伴
    0.47
     imate
    0.47
     interrupts
    0.46
    Đi
    0.46
    殳
    0.45
     máte
    0.44
    而去
    0.43
    儸
    0.43
    _{
    0.43
    POSITIVE LOGITS
     affirm
    0.46
     கூ
    0.45
     تیس
    0.43
    publik
    0.42
    品番
    0.42
    ten
    0.41
    ningen
    0.41
    pur
    0.41
    nty
    0.41
     अभिकथन
    0.40
    Activations Density 0.001%

    No Known Activations