© 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. 212702
    Prev
    Next
    INDEX
    Explanations

    submission of tender

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

    language or text constructs

    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
    ي
    0.46
     خاندان
    0.46
     giống
    0.45
     οικο
    0.45
     یون
    0.44
     خانواده
    0.44
    thiaz
    0.44
     macros
    0.44
     تتع
    0.44
     అలాగే
    0.43
    POSITIVE LOGITS
     sende
    0.47
    าส
    0.46
     send
    0.46
    a
    0.43
    send
    0.42
     Colombe
    0.42
    更好的
    0.42
    adocia
    0.41
    oki
    0.41
    不出
    0.41
    Activations Density 0.001%

    No Known Activations