© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11059
    Prev
    Next
    INDEX
    Explanations

    frontfront hallfront entryfront facingfront of the housefront-endfront-line

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

    front-end, frontrunner, front lines

    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_40_width_16k_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
    尾
    0.43
    vär
    0.40
    背
    0.39
    ('=
    0.39
    ภัย
    0.38
    bgColor
    0.38
    eal
    0.37
    {~
    0.37
    Tail
    0.37
     appellee
    0.37
    POSITIVE LOGITS
     front
    1.38
     Front
    1.33
    front
    1.23
     фрон
    1.22
    Front
    1.21
     फ्रंट
    1.16
     FRONT
    1.14
    FRONT
    1.13
     fronts
    1.08
    フロント
    1.08
    Activations Density 0.119%

    No Known Activations