© 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. 70841
    Prev
    Next
    INDEX
    Explanations

    responsible for, secure a, approaches, saving

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

    knowing the structure

    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
     ngọt
    0.46
    ্যাস
    0.43
     afectar
    0.42
    *****",
    0.42
    tamil
    0.41
     attham
    0.41
    kommer
    0.41
     flera
    0.40
    abhavena
    0.40
    ént
    0.40
    POSITIVE LOGITS
     სახელმწიფ
    0.54
    サム
    0.50
    상의
    0.49
     scandal
    0.48
    ジタル
    0.47
    制御
    0.47
    에서의
    0.46
     ხელისუფლების
    0.46
    ਣ
    0.46
     subspace
    0.46
    Activations Density 0.001%

    No Known Activations