© 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. 179017
    Prev
    Next
    INDEX
    Explanations

    Globe Awards

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

    very common, very effective

    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
     പറയ
    0.53
     시간이
    0.52
     amacı
    0.50
     기도
    0.50
    度の
    0.49
    ༠
    0.49
     খ্র
    0.48
     আনন্দের
    0.48
    lä
    0.48
     電力
    0.47
    POSITIVE LOGITS
    ной
    0.47
    司
    0.46
    ный
    0.46
    வும்
    0.46
    ypen
    0.45
     Squared
    0.45
    वेज
    0.44
    یں
    0.43
     قرار
    0.43
     burdened
    0.41
    Activations Density 0.000%

    No Known Activations