© 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. 138814
    Prev
    Next
    INDEX
    Explanations

    based on, zek, on

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

    `details` `answer` `recall` `single`

    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
     woman
    0.49
     persistently
    0.48
     till
    0.48
     v
    0.48
     forest
    0.47
     al
    0.47
     voit
    0.46
     sweet
    0.45
     luckily
    0.45
     woods
    0.44
    POSITIVE LOGITS
    ໄປ
    0.59
     રાશિફળ
    0.53
    loj
    0.52
    凯
    0.52
    哆
    0.52
    绘制
    0.52
     સંખ્યા
    0.51
    Eid
    0.51
    훌
    0.50
    뽐
    0.50
    Activations Density 0.001%

    No Known Activations