© 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. 221552
    Prev
    Next
    INDEX
    Explanations

    specific designs, economy practice, kids doing

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

    batches, variations, limits

    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
    (
    0.59
    {
    0.52
     steered
    0.47
     steer
    0.43
     steering
    0.42
    。
    0.41
     lived
    0.41
    :
    0.41
     streamlit
    0.40
    اك
    0.40
    POSITIVE LOGITS
    Variables
    0.56
     אז
    0.54
    <unused79>
    0.54
     உருவாக
    0.53
     महानगर
    0.52
     галакти
    0.51
    炡
    0.51
    Operation
    0.51
     গভর্নর
    0.51
     నెల
    0.50
    Activations Density 0.000%

    No Known Activations