© 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-262K
    7. 128701
    Prev
    Next
    INDEX
    Explanations

    danger, Amy, Task, Information

    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
     Julian
    0.45
    cH
    0.44
    ႂ
    0.44
    жат
    0.43
     Chúa
    0.42
     Montana
    0.41
     trochu
    0.41
     Parkinson
    0.40
    र्जा
    0.40
     krzy
    0.39
    POSITIVE LOGITS
    であり
    0.53
    Пере
    0.51
    ก
    0.50
    पर
    0.49
    utations
    0.46
    Зак
    0.45
     කිරීම
    0.44
    ক
    0.44
    स
    0.44
    Accum
    0.43
    Activations Density 0.003%

    No Known Activations