© 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. 96715
    Prev
    Next
    INDEX
    Explanations

    copyright storm, recipient, diabetes

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

    publishing and related topics

    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
    -
    0.54
     ail
    0.47
    il
    0.46
    ;
    0.45
    ᱝ
    0.44
    program
    0.44
    im
    0.44
    fat
    0.43
     accidentally
    0.43
     fat
    0.43
    POSITIVE LOGITS
    इससे
    0.53
    ⦕
    0.53
    如下图
    0.52
    Ē
    0.52
    फ्रा
    0.52
    쨰
    0.51
     گویا
    0.51
    چین
    0.50
     تاہم
    0.50
    اردوش
    0.49
    Activations Density 0.000%

    No Known Activations