© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9094
    Prev
    Next
    INDEX
    Explanations

    pen and pencil

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    カード
    0.44
    ुर
    0.42
     escalation
    0.42
     कार्ड
    0.40
    elfare
    0.39
    decoded
    0.38
    <0x9A>
    0.38
     inflating
    0.38
     cardia
    0.37
     カード
    0.37
    POSITIVE LOGITS
     pencil
    1.48
     pencils
    1.45
     pen
    1.40
     Pencil
    1.39
     قلم
    1.30
    笔
    1.28
    pencil
    1.27
     pens
    1.23
    筆
    1.23
     पेंसिल
    1.21
    Activations Density 0.123%

    No Known Activations