© 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. 131849
    Prev
    Next
    INDEX
    Explanations

    privacy, copyright, links, personal, online

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

    constant, verbal response, quality, casual

    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
     Congreg
    0.48
     ministries
    0.44
     ministère
    0.44
    もら
    0.43
    ärten
    0.42
    醀
    0.42
    ဌ
    0.42
    ᙱ
    0.42
     culturally
    0.41
    祠
    0.41
    POSITIVE LOGITS
     gato
    0.51
     nums
    0.47
    INO
    0.46
    ່ວນ
    0.46
    ID
    0.45
    dm
    0.45
     了
    0.43
    ORT
    0.43
    yt
    0.43
    wang
    0.42
    Activations Density 0.001%

    No Known Activations