© 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. 73350
    Prev
    Next
    INDEX
    Explanations

    numbers or letters followed by specific words

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

    change and theory

    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
    elwv
    0.54
     आर्टिकल
    0.50
    너
    0.50
     Ambris
    0.48
     রামগতি
    0.47
    নে
    0.46
    nés
    0.46
     niem
    0.46
    <0xA0>
    0.46
     السي
    0.46
    POSITIVE LOGITS
    0.72
     s
    0.53
    0
    0.53
     a
    0.50
     FAV
    0.50
     is
    0.50
     JACK
    0.50
    -
    0.49
    _
    0.48
    VECTOR
    0.46
    Activations Density 0.001%

    No Known Activations