© 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. 16393
    Prev
    Next
    INDEX
    Explanations

    programming or code contexts

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

    fits into understanding

    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
     هنت
    0.64
     chom
    0.53
     Whiting
    0.48
    enek
    0.48
    亨
    0.47
     Villiers
    0.47
     Columb
    0.47
     Domen
    0.47
    organic
    0.46
    eney
    0.46
    POSITIVE LOGITS
     strlen
    0.58
    ლ
    0.45
     widths
    0.44
     angepasst
    0.43
     strcmp
    0.40
    <?=$
    0.40
    US
    0.40
    )?,
    0.40
    LE
    0.40
     $("#
    0.39
    Activations Density 0.000%

    No Known Activations