© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92383
    Prev
    Next
    INDEX
    Explanations

    Terms of Service, violation, Events

    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
     consigui
    0.42
     competitions
    0.41
     la
    0.41
     l
    0.40
     cambia
    0.40
     ogrom
    0.40
     wodurch
    0.40
     puedes
    0.39
     T
    0.39
     yani
    0.39
    POSITIVE LOGITS
     ਅਤੇ
    0.57
    และ
    0.56
     и
    0.50
     һәм
    0.50
     และ
    0.50
     પણ
    0.50
     және
    0.50
     आणि
    0.49
     και
    0.49
    และความ
    0.47
    Activations Density 0.012%

    No Known Activations