© 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. 400
    Prev
    Next
    INDEX
    Explanations

    file types and website metadata

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

    file types and extensions

    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
    챱
    0.24
    מונה
    0.23
    怎麼樣
    0.23
     namani
    0.23
     Bartholom
    0.23
     kebij
    0.23
    Imidazole
    0.23
    ्हान
    0.23
     assass
    0.23
    Gosudarstvennyj
    0.23
    POSITIVE LOGITS
    jpg
    0.38
    html
    0.37
    png
    0.32
    exe
    0.32
    ized
    0.30
    V
    0.30
    지
    0.30
    io
    0.30
    ai
    0.29
     Букмекердик
    0.29
    Activations Density 0.740%

    No Known Activations