© 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. 116118
    Prev
    Next
    INDEX
    Explanations

    rest in peace

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

    worship, little, slightly, sloping

    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
    ్యాచ్
    0.55
    适当
    0.50
     driv
    0.47
     compléter
    0.47
    Appropri
    0.47
    琏
    0.46
    愆
    0.46
     simb
    0.46
    ולי
    0.46
    为
    0.46
    POSITIVE LOGITS
     Kaduna
    0.48
     สืบค้น
    0.46
    promoting
    0.44
     PMID
    0.44
     いき
    0.44
     Nagar
    0.44
     separatist
    0.43
    elcome
    0.43
     Iraqi
    0.43
     Needham
    0.42
    Activations Density 0.001%

    No Known Activations