© 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-65K
    7. 62228
    Prev
    Next
    INDEX
    Explanations

    simple functionality

    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_65k_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
     the
    0.47
    the
    0.41
    VALUE
    0.41
     prevista
    0.40
    your
    0.40
     nový
    0.40
    §
    0.40
    브
    0.40
     your
    0.39
    Section
    0.39
    POSITIVE LOGITS
     Kardashians
    0.48
     cookbooks
    0.47
     Beyoncé
    0.47
     Мари
    0.46
     countertops
    0.46
     Cowboys
    0.45
     girly
    0.45
     कार्ब
    0.45
     veggies
    0.43
     ఎక్కువగా
    0.43
    Activations Density 0.005%

    No Known Activations