© 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. 111739
    Prev
    Next
    INDEX
    Explanations

    removal, observing, eliminated

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

    aftermath of, placed, importance, de

    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
     दर्पण
    0.55
    З
    0.50
     காட்ச
    0.50
     xhrObj
    0.49
     졸
    0.48
     hr
    0.48
     з
    0.48
     કેટલાક
    0.47
     схе
    0.47
     serpentine
    0.47
    POSITIVE LOGITS
    واء
    0.51
    what
    0.49
    غط
    0.46
    ww
    0.45
    一款
    0.45
    携
    0.45
    وني
    0.44
    限量
    0.43
    exact
    0.43
    حدة
    0.42
    Activations Density 0.000%

    No Known Activations