© 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. 31-GEMMASCOPE-2-RES-16K
    7. 13672
    Prev
    Next
    INDEX
    Explanations

    news urls

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

    adoption rate

    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_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
    ย
    0.52
     लड़कियों
    0.49
    ៤
    0.49
    LAN
    0.48
     المد
    0.48
    CENT
    0.47
     Appalachian
    0.46
    ifornia
    0.46
     допомо
    0.46
    DARK
    0.46
    POSITIVE LOGITS
    ocomplete
    0.48
    atta
    0.46
    údo
    0.46
    getResult
    0.46
    ómo
    0.46
    뤽
    0.45
    ümer
    0.45
    vres
    0.44
    árez
    0.44
    jsr
    0.44
    Activations Density 0.002%

    No Known Activations