© 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. 8781
    Prev
    Next
    INDEX
    Explanations

    takechurcharch

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

    AI assistants and GPT models

    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
     -
    0.64
    -
    0.59
     k
    0.53
    s
    0.52
    q
    0.50
    to
    0.49
    est
    0.49
    Worth
    0.49
    i
    0.49
    U
    0.49
    POSITIVE LOGITS
     imassa
    0.61
     núcle
    0.58
     ettha
    0.58
     renouvel
    0.52
     carbohyd
    0.51
     polype
    0.51
    ंख्य
    0.50
     caloric
    0.50
     falleció
    0.50
     sepd
    0.48
    Activations Density 0.000%

    No Known Activations