© 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. 146309
    Prev
    Next
    INDEX
    Explanations

    dense than

    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
     Rā
    0.45
    प्ले
    0.44
     Aś
    0.43
    âmara
    0.42
    ాల్
    0.41
     romp
    0.41
     menyer
    0.40
     Ś
    0.40
    लाब
    0.40
    ਾਨੂੰ
    0.39
    POSITIVE LOGITS
    mobile
    0.48
    socks
    0.45
    goog
    0.43
    sock
    0.43
    messages
    0.43
    intos
    0.42
    text
    0.41
    homepage
    0.41
    ts
    0.39
    tree
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.