© 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. 200146
    Prev
    Next
    INDEX
    Explanations

    numbers and words like years, bus

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

    request access to data or email

    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
    طلاق
    0.45
     النظام
    0.43
     patties
    0.43
     systému
    0.42
    を通
    0.42
     inns
    0.41
    賂
    0.41
    レア
    0.40
    通過
    0.40
    তান
    0.40
    POSITIVE LOGITS
    ży
    0.50
    ſs
    0.47
    even
    0.46
    ſt
    0.44
    他也
    0.44
     Seç
    0.41
    ſh
    0.41
    他在
    0.41
    rhs
    0.41
     सुद्धा
    0.41
    Activations Density 0.000%

    No Known Activations