© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 14802
    Prev
    Next
    INDEX
    Explanations

    file named

    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
    ᱕
    0.91
    ᱖
    0.91
    ᱓
    0.90
    ᱗
    0.90
    ра
    0.90
    را
    0.88
    스
    0.86
    ᱘
    0.86
    ޏ
    0.84
    ری
    0.84
    POSITIVE LOGITS
    P
    0.94
    L
    0.93
    R
    0.92
    N
    0.82
    S
    0.80
    M
    0.77
    T
    0.76
    uk
    0.74
    AB
    0.73
     by
    0.72
    Activations Density 0.074%

    No Known Activations