© 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. 55326
    Prev
    Next
    INDEX
    Explanations

    early symptoms of development

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

    if you, Calcium Hydro, bring them

    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
    SA
    0.48
    Sample
    0.48
    Gordon
    0.46
    بار
    0.46
    Samuel
    0.45
    A
    0.45
    Smart
    0.44
    Something
    0.44
    Spencer
    0.44
    CSP
    0.44
    POSITIVE LOGITS
    }}}=\
    0.49
     przyjem
    0.49
    텨
    0.48
    飥
    0.48
    老大
    0.46
    वेलकम
    0.45
    GEBURTS
    0.45
    supseteq
    0.45
    forderungen
    0.45
     AppBsky
    0.44
    Activations Density 0.000%

    No Known Activations