© 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. 4593
    Prev
    Next
    INDEX
    Explanations

    UTF-8 encoding

    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
    <unused50>
    0.54
     sécrétion
    0.53
     carinatis
    0.52
     صہیونیوں
    0.51
    [multimodal]
    0.51
     行っ
    0.50
     رجسٹ
    0.50
     ferrugineux
    0.50
     تړل
    0.50
     testaceis
    0.49
    POSITIVE LOGITS
    E
    0.57
     at
    0.56
    o
    0.56
      
    0.54
    and
    0.54
     Transient
    0.53
     The
    0.52
     present
    0.52
    0.52
    ’
    0.52
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.