© 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. 138638
    Prev
    Next
    INDEX
    Explanations

    Hajj, Magical Mushrooms, explained next, Memory Stick, scheduling

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

    states, qualities, or negations

    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
    AssetsRequest
    0.46
     appease
    0.45
     poset
    0.45
     dine
    0.44
    __(/*!
    0.43
     ?!
    0.43
     đoàn
    0.42
     Goldberg
    0.42
     el
    0.42
     fe
    0.42
    POSITIVE LOGITS
    لاحظ
    0.50
    غت
    0.47
    نت
    0.46
    мента
    0.46
    وت
    0.46
    ૫
    0.45
    𝘻
    0.45
    ྪ
    0.45
     তাহাতে
    0.44
    tractor
    0.44
    Activations Density 0.001%

    No Known Activations