© 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. 157832
    Prev
    Next
    INDEX
    Explanations

    comma then

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

    technical documentation and advice

    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
     revision
    0.50
     jumlah
    0.47
     flanges
    0.47
     president
    0.46
     outbreak
    0.45
    m
    0.45
     to
    0.44
     mutual
    0.44
     message
    0.44
     para
    0.43
    POSITIVE LOGITS
     эту
    0.48
     இந்தப்
    0.47
    ЛИ
    0.46
    坵
    0.45
     ጣ
    0.45
     ওই
    0.45
    隘
    0.45
    酘
    0.45
    ghum
    0.44
    testen
    0.44
    Activations Density 0.001%

    No Known Activations