© 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. 211187
    Prev
    Next
    INDEX
    Explanations

    removable covers or handles

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

    conversation context management

    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
     وكانت
    0.52
     damal
    0.52
     一个
    0.48
     ම
    0.48
     وكان
    0.47
    样例
    0.46
     তখনও
    0.46
     было
    0.45
    还是
    0.44
     Carpet
    0.44
    POSITIVE LOGITS
    𝗴
    0.45
    mold
    0.43
    ಗು
    0.42
    𝔦
    0.41
    twitch
    0.41
    isk
    0.40
    yip
    0.40
    lur
    0.40
    warz
    0.40
    劇
    0.39
    Activations Density 0.002%

    No Known Activations