© 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. 133660
    Prev
    Next
    INDEX
    Explanations

    skip the missed dose if

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

    ad headline templates

    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
    ദാ
    0.42
    徐
    0.42
    approach
    0.41
    伥
    0.41
     керу
    0.40
    ூ
    0.40
    ysc
    0.40
    Yok
    0.40
    バ
    0.40
     popupButton
    0.39
    POSITIVE LOGITS
     intellectually
    0.52
    ဖြစ်
    0.45
    علوم
    0.44
     Regina
    0.43
    뚱
    0.43
     Frankfort
    0.43
     Joan
    0.42
    বিদ্যাল
    0.41
     domést
    0.40
     Saskatoon
    0.40
    Activations Density 0.001%

    No Known Activations