© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9349
    Prev
    Next
    INDEX
    Explanations

    song titles and movie review snippets

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

    first part of term

    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
    SqlServer
    0.37
    ູບ
    0.37
    </em>
    0.35
    zl
    0.35
    țională
    0.34
    VhZ
    0.34
    obb
    0.34
    ABCDEFGHIJKLMNOP
    0.34
    mapped
    0.34
    뮐
    0.33
    POSITIVE LOGITS
    ান্তরে
    0.50
    ချင်း
    0.48
     Henning
    0.47
     amal
    0.43
     kri
    0.42
     Eugenio
    0.41
     மாறு
    0.41
    icides
    0.40
    lığını
    0.40
    ếc
    0.40
    Activations Density 0.484%

    No Known Activations