© 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. 217403
    Prev
    Next
    INDEX
    Explanations

    most important

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

    probability and duplicates

    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
     this
    0.47
     begins
    0.46
     spirit
    0.46
     affid
    0.45
     ç
    0.45
    รถ
    0.44
     bhaj
    0.44
     roz
    0.44
     çal
    0.43
    >{
    0.43
    POSITIVE LOGITS
     телеви
    0.49
    𝓀
    0.49
     Sebastián
    0.47
    पोस्ट
    0.46
     थकान
    0.46
    🦦
    0.45
    widget
    0.45
     Óscar
    0.44
    textures
    0.44
    最高的
    0.43
    Activations Density 0.001%

    No Known Activations