© 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. 81471
    Prev
    Next
    INDEX
    Explanations

    constellations and volume

    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
    ้าย
    0.44
     ৭
    0.43
     muitos
    0.43
    亳
    0.43
     microseconds
    0.42
     resellers
    0.42
     များ
    0.42
    크
    0.42
     mètres
    0.41
    对他
    0.41
    POSITIVE LOGITS
     regain
    0.52
     confronted
    0.45
    िट
    0.45
     skeleton
    0.42
    ile
    0.42
     blockade
    0.42
    ע
    0.41
     regained
    0.41
    经历了
    0.41
    рое
    0.40
    Activations Density 0.008%

    No Known Activations