© 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. 117153
    Prev
    Next
    INDEX
    Explanations

    transitions and outcomes

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

    just feeling

    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
     車
    0.56
     Mehta
    0.50
     NTR
    0.50
     AIA
    0.50
     Fisheries
    0.48
     微
    0.48
    িনি
    0.48
     牛
    0.48
     신
    0.46
     기본
    0.46
    POSITIVE LOGITS
    ard
    0.50
    ilg
    0.49
    ag
    0.48
    igrams
    0.48
    aten
    0.46
    emois
    0.46
    ar
    0.45
     ख्याल
    0.45
    żli
    0.45
    urna
    0.45
    Activations Density 0.001%

    No Known Activations