© 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. 155804
    Prev
    Next
    INDEX
    Explanations

    support team analysts brothers

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

    niche, issues, gap, compounds, Schools, oxide

    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
    летие
    0.53
    來
    0.52
    ாலை
    0.48
     Đế
    0.47
     हिसाब
    0.46
     कौर
    0.46
    淪
    0.44
    politics
    0.44
    غرافيا
    0.42
    邢
    0.42
    POSITIVE LOGITS
    ร้อม
    0.53
     nal
    0.48
     chromatic
    0.48
     racemic
    0.47
     tablet
    0.47
     cDNA
    0.47
     diter
    0.46
     glassy
    0.46
     printr
    0.45
     eller
    0.44
    Activations Density 0.000%

    No Known Activations