© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 50619
    Prev
    Next
    INDEX
    Explanations

    standard | detailed | inflammation | experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pier
    0.47
    ъ
    0.46
    يفة
    0.45
    関数
    0.44
    ِي
    0.44
    3
    0.44
     formular
    0.43
    㣫
    0.43
    ival
    0.42
     Freeman
    0.42
    POSITIVE LOGITS
     पाक
    0.47
    बित
    0.46
    aas
    0.46
     maatau
    0.45
    드렸
    0.44
     کاغذ
    0.43
    centage
    0.43
     путем
    0.42
    a
    0.42
    কাম
    0.41
    Activations Density 0.002%

    No Known Activations