© 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. 121982
    Prev
    Next
    INDEX
    Explanations

    Moose or Bison, hairband, through security

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

    describes followed by noun

    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
    rook
    0.41
     ona
    0.41
    een
    0.40
     clings
    0.39
    羽
    0.39
    ﹀
    0.38
     carga
    0.38
     어린
    0.38
     స్టార్
    0.38
    nae
    0.38
    POSITIVE LOGITS
    क्षिक
    0.57
     kebijakan
    0.48
     interpretations
    0.48
    “-
    0.46
    ذی
    0.45
    пот
    0.45
    পক্ষে
    0.44
     بنیادی
    0.44
     Interpret
    0.44
    ācijas
    0.44
    Activations Density 0.000%

    No Known Activations