© 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. 184639
    Prev
    Next
    INDEX
    Explanations

    undisclosed liabilities, online ticketing, local communities

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

    Where

    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
     Versuch
    0.49
     AcOH
    0.49
     rozwoju
    0.46
    latego
    0.45
    濘
    0.45
     Technik
    0.45
    તાવ
    0.45
     inoxyd
    0.44
     উপহার
    0.43
    重點
    0.43
    POSITIVE LOGITS
    äng
    0.49
     phone
    0.46
    compassing
    0.46
    切り
    0.46
    越
    0.44
     patient
    0.44
     Scotland
    0.43
     satellite
    0.42
    patient
    0.42
     started
    0.41
    Activations Density 0.000%

    No Known Activations