© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 169841
    Prev
    Next
    INDEX
    Explanations

    reserve for

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

    building and rebuilding

    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
    وا
    0.55
    buscador
    0.52
    多久
    0.52
    ಡ
    0.48
    quil
    0.48
    វ
    0.47
    ង្វ
    0.47
     modelos
    0.46
    هم
    0.46
    время
    0.46
    POSITIVE LOGITS
     Phi
    0.46
    );//
    0.45
     Identification
    0.45
     Telephone
    0.45
     Literacy
    0.43
     แต
    0.43
     ปุ่ม
    0.43
    리기
    0.43
     Clarks
    0.42
    蓥
    0.42
    Activations Density 0.001%

    No Known Activations