© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 143388
    Prev
    Next
    INDEX
    Explanations

    architect, routes, men, photo, spouses, Instagram

    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
     مقابلے
    0.43
     asymmetrical
    0.41
     سيكون
    0.41
     بالج
    0.41
    債
    0.41
     る
    0.40
     कामकाज
    0.40
    頡
    0.40
     corresponds
    0.39
    ąż
    0.39
    POSITIVE LOGITS
    ONDER
    0.53
    ONDON
    0.46
    也可以
    0.45
    સ્ક
    0.45
     NOTICE
    0.44
    arctic
    0.44
    PUR
    0.44
     encontrar
    0.42
    sons
    0.42
    vens
    0.42
    Activations Density 0.004%

    No Known Activations