© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 126749
    Prev
    Next
    INDEX
    Explanations

    vpn, branding, fantasy sports, gaming, software

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

    acknowledging a surprisingly complex question

    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
    ѕ
    0.49
    5
    0.47
    and
    0.47
    yn
    0.47
    ans
    0.45
    3
    0.45
    cs
    0.44
    wyn
    0.44
    ;
    0.43
    ps
    0.43
    POSITIVE LOGITS
     请求
    0.39
     inhomogeneity
    0.37
    短暂
    0.36
     genealog
    0.35
     pluripotent
    0.35
     chandeliers
    0.35
    ุล
    0.35
     decomposes
    0.35
     생각
    0.35
     raindrops
    0.35
    Activations Density 0.003%

    No Known Activations