© 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. 107440
    Prev
    Next
    INDEX
    Explanations

    particular climate

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

    period, cosmic, resolves, $

    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
     मधुमेह
    0.52
     problemy
    0.50
    轵
    0.50
     большие
    0.50
    هم
    0.49
    ূপ
    0.49
     चिकन
    0.49
     घना
    0.49
    কেমিক্যাল
    0.49
     गुड
    0.49
    POSITIVE LOGITS
     n
    0.51
     removed
    0.50
    ↓
    0.49
    ↑
    0.47
    ier
    0.46
     ↓
    0.43
     saber
    0.41
     tastes
    0.40
     cre
    0.40
     dest
    0.39
    Activations Density 0.000%

    No Known Activations