© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 95582
    Prev
    Next
    INDEX
    Explanations

    sales literature, head nod, low scoring

    np_acts-logits-general · gemini-2.5-flash-lite

    gendered search, initialize state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    সমূ
    0.46
     რომელი
    0.45
    os
    0.44
    working
    0.43
    u
    0.43
    ให้บริการ
    0.43
    od
    0.42
     Mén
    0.42
    迄
    0.42
    spanning
    0.42
    POSITIVE LOGITS
     aggressively
    0.57
     flashy
    0.56
     criança
    0.55
     energía
    0.54
     agress
    0.54
     энергии
    0.52
     energie
    0.52
     energii
    0.52
     catchy
    0.51
     kid
    0.50
    Activations Density 0.001%

    No Known Activations