© 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. 209982
    Prev
    Next
    INDEX
    Explanations

    group membership and visitors

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

    additional or unofficial members

    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
     investigaciones
    0.38
    বারের
    0.38
    alignParentRight
    0.38
    
    0.37
    চ্ছিলাম
    0.37
    जेस्टिव
    0.37
    漲
    0.37
     glassy
    0.36
    癀
    0.36
    leye
    0.36
    POSITIVE LOGITS
     outsiders
    0.75
     Auxiliary
    0.70
    invited
    0.69
     guest
    0.67
     invited
    0.66
     auxiliary
    0.64
     non
    0.64
     Honorary
    0.64
     auxili
    0.64
     Invited
    0.64
    Activations Density 0.270%

    No Known Activations