© 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. 233915
    Prev
    Next
    INDEX
    Explanations

    network, OS, UNIX, financial, currently

    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
     can
    0.57
     chart
    0.50
     皆
    0.49
     taff
    0.48
     збіль
    0.47
     reduce
    0.46
     roadway
    0.46
     T
    0.46
     sculpture
    0.45
     map
    0.45
    POSITIVE LOGITS
    éricos
    0.48
    ਲੀ
    0.48
    ábbi
    0.47
    涷
    0.47
    尴
    0.47
    slüman
    0.47
    ativistic
    0.46
    elige
    0.46
    érico
    0.46
    betriebnahme
    0.46
    Activations Density 0.001%

    No Known Activations