© 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-16K
    7. 3960
    Prev
    Next
    INDEX
    Explanations

    version numbers in code

    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_16k_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
    マト
    0.51
    ิ
    0.47
    леты
    0.45
     cites
    0.44
    твы
    0.43
    繧
    0.43
     determin
    0.43
     complexities
    0.42
     autres
    0.42
    その他
    0.42
    POSITIVE LOGITS
    0
    0.44
    flap
    0.40
     କରି
    0.39
     Caller
    0.39
    resign
    0.39
     دقت
    0.39
    lable
    0.39
    接
    0.39
     winding
    0.38
     सर्वा
    0.38
    Activations Density 0.022%

    No Known Activations