© 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. 91881
    Prev
    Next
    INDEX
    Explanations

    wrapping up or around

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

    uncomfortable, just, earlier, nodes, rating

    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
    𝘷
    0.63
     gstlal
    0.61
    스의
    0.60
    <unused45>
    0.59
     ऑब्जेक्ट
    0.57
    <unused22>
    0.57
     Especific
    0.57
    괵
    0.55
    缟
    0.54
    𝓜
    0.54
    POSITIVE LOGITS
     I
    0.61
    ↵
    0.61
    0.54
     storm
    0.54
     K
    0.52
     dusting
    0.51
     =
    0.50
     Center
    0.50
     U
    0.49
     Westminster
    0.49
    Activations Density 0.000%

    No Known Activations