© 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. 191398
    Prev
    Next
    INDEX
    Explanations

    discretion without

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

    printable art, US legal, minimizing risk

    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
    holomorphic
    0.50
     imperatives
    0.49
    鉀
    0.48
    argout
    0.46
    ellidos
    0.46
    dequeue
    0.45
    simeq
    0.45
     購入
    0.44
     माइनस
    0.44
    aspis
    0.44
    POSITIVE LOGITS
     كلمة
    0.53
     çalışt
    0.51
     gestaltet
    0.45
     وحده
    0.43
    8
    0.42
     yaparak
    0.41
     रहकर
    0.40
     cerr
    0.39
    인지
    0.39
     Cerv
    0.39
    Activations Density 0.000%

    No Known Activations