© 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. 11870
    Prev
    Next
    INDEX
    Explanations

    transit times

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

    urgency, awareness, resilience, communicating

    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
    de
    0.69
    ma
    0.61
    d
    0.61
    g
    0.59
    b
    0.58
    z
    0.58
    n
    0.56
    indent
    0.55
    id
    0.55
    eta
    0.54
    POSITIVE LOGITS
     banheiro
    0.61
     సామ
    0.55
    <start_of_turn>
    0.52
     dajj
    0.51
     könny
    0.50
    ുപത്രി
    0.49
     îmb
    0.49
     ruchu
    0.49
    iyaç
    0.49
     తయారు
    0.49
    Activations Density 0.000%

    No Known Activations