© 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. 177188
    Prev
    Next
    INDEX
    Explanations

    welcome Acrylic

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

    BREAKDOWN SECTIONS AND LISTS

    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
     noticing
    0.44
    Eigen
    0.43
    Archer
    0.43
    coff
    0.40
    𝚔
    0.40
     thumbnails
    0.40
     자신의
    0.40
    corre
    0.40
    corr
    0.39
    你也
    0.39
    POSITIVE LOGITS
     сообщает
    0.51
     EPL
    0.49
     Patents
    0.48
     émotion
    0.48
    ం
    0.48
     Bens
    0.47
     ทั้ง
    0.47
     включают
    0.47
     são
    0.46
     控制
    0.46
    Activations Density 0.000%

    No Known Activations