© 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. 137047
    Prev
    Next
    INDEX
    Explanations

    describing abstract concepts and actions

    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
     yapılacak
    0.43
     ramping
    0.43
    ל
    0.42
    ても
    0.41
    值得
    0.41
    ירות
    0.41
     bubbles
    0.41
    这个
    0.40
     nuovi
    0.40
    ited
    0.39
    POSITIVE LOGITS
     discrepancies
    0.45
     Australia
    0.44
     Liefer
    0.43
     Copern
    0.43
     voluntarily
    0.42
     discrep
    0.42
    盥
    0.42
     Duch
    0.41
     gesetz
    0.41
     Normal
    0.41
    Activations Density 0.008%

    No Known Activations