© 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. 70082
    Prev
    Next
    INDEX
    Explanations

    potential outside, concept by

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

    rice vanilla reach

    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
     corrupted
    0.48
    Ს
    0.47
    смотреть
    0.44
    ᴘ
    0.43
    ッパー
    0.42
     diem
    0.41
    Ö
    0.41
     intelligent
    0.41
    kommer
    0.41
    ि
    0.41
    POSITIVE LOGITS
     InputListener
    0.46
    会让
    0.45
     சின்ன
    0.44
     Dann
    0.44
     ottobre
    0.44
    員
    0.42
    能否
    0.41
    比例
    0.41
    住了
    0.41
    နယ်
    0.41
    Activations Density 0.000%

    No Known Activations