© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 35033
    Prev
    Next
    INDEX
    Explanations

    project, technology, tables, meme

    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_262k_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
    ل
    0.52
     agglut
    0.51
    的
    0.50
     ions
    0.48
    ↵↵
    0.47
    ة
    0.46
     of
    0.46
    ες
    0.46
    0.46
    zt
    0.45
    POSITIVE LOGITS
    bersihan
    0.47
    maja
    0.45
     또한
    0.45
     Izv
    0.44
    iranja
    0.42
     சம்பந்த
    0.42
     ನಾನು
    0.42
     SPDX
    0.42
    මට
    0.41
     предме
    0.41
    Activations Density 0.000%

    No Known Activations