© 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. 132875
    Prev
    Next
    INDEX
    Explanations

    when comes list

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

    Chrome OS

    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
     Spitzen
    0.49
    dem
    0.48
    _
    0.47
    ue
    0.47
    -
    0.46
    ubble
    0.45
    em
    0.44
     demi
    0.44
     दिव्यांग
    0.42
    hem
    0.42
    POSITIVE LOGITS
     пои
    0.47
    ᄂ
    0.46
    сног
    0.44
     своим
    0.44
    ൯
    0.43
    pOt
    0.43
     rags
    0.43
    かと
    0.42
    става
    0.42
    க்கணக்கான
    0.42
    Activations Density 0.001%

    No Known Activations