© 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. 155218
    Prev
    Next
    INDEX
    Explanations

    financial and technical details

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

    descriptive phrases or associations

    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
    펙
    0.54
     νέ
    0.53
    عی
    0.51
    τές
    0.51
    ρκ
    0.48
     projecting
    0.48
    kkal
    0.47
    ইহার
    0.47
    رش
    0.47
    选手
    0.46
    POSITIVE LOGITS
    </b>
    0.51
     ۾
    0.51
    ii
    0.50
    iyorum
    0.49
     ,
    0.48
    igens
    0.48
     .
    0.48
     (
    0.47
    </h4>
    0.47
    ција
    0.47
    Activations Density 0.001%

    No Known Activations