© 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. 135853
    Prev
    Next
    INDEX
    Explanations

    orbits and ellipses

    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
    颢
    0.50
    Both
    0.47
     یا
    0.46
     کشمیر
    0.46
    韩
    0.45
    یثیت
    0.45
    Comunic
    0.44
    
    0.43
    یو
    0.43
     interplanetary
    0.43
    POSITIVE LOGITS
     dress
    0.42
     sli
    0.42
     С
    0.41
     STILL
    0.41
    onka
    0.41
    રો
    0.40
     बँ
    0.40
     scrubbing
    0.40
     stress
    0.39
     extremely
    0.39
    Activations Density 0.013%

    No Known Activations