© 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. 163663
    Prev
    Next
    INDEX
    Explanations

    multilingual words

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

    multi-purpose verbs

    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
    aeskeygenassist
    0.49
    along
    0.49
    agory
    0.47
    ALL
    0.45
    ccbp
    0.45
    abv
    0.44
    }^{+
    0.44
     అత
    0.43
     أيضا
    0.43
     также
    0.43
    POSITIVE LOGITS
    ینو
    0.50
     dokter
    0.48
     arbej
    0.46
    小时
    0.44
    编写
    0.44
    长期
    0.44
    医生
    0.43
     døde
    0.43
    战士
    0.43
    报警
    0.42
    Activations Density 0.002%

    No Known Activations