© 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. 212676
    Prev
    Next
    INDEX
    Explanations

    ISBN and technical terms

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

    pass

    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
    ς
    0.52
    房子
    0.51
    mysql
    0.50
    sd
    0.47
    SAN
    0.47
    mimpi
    0.46
    S
    0.46
    L
    0.46
    申請
    0.45
    observed
    0.44
    POSITIVE LOGITS
     жүктөп
    0.48
     dưỡng
    0.46
     كلام
    0.46
    abilités
    0.45
     متعدد
    0.45
     дале
    0.45
     multiplicación
    0.44
     prévention
    0.44
     Clipboard
    0.44
     artériel
    0.43
    Activations Density 0.001%

    No Known Activations