© 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. 109702
    Prev
    Next
    INDEX
    Explanations

    social gatherings and membership

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

    personal and industrial concepts

    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
    다고
    0.55
    なかった
    0.52
     fortiter
    0.52
    💓
    0.50
    인다
    0.49
    ❤❤
    0.49
    不堪
    0.49
    ے
    0.49
    வியில்
    0.48
    ுடைய
    0.48
    POSITIVE LOGITS
    roll
    0.50
    rogen
    0.49
     Skin
    0.47
    ido
    0.45
    st
    0.45
     R
    0.45
    tot
    0.44
    iring
    0.44
     Optimized
    0.44
    roi
    0.43
    Activations Density 0.000%

    No Known Activations