© 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. 209202
    Prev
    Next
    INDEX
    Explanations

    funny celebrities, little pens

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

    psych, yaml, and gui

    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
    কালীন
    0.51
    νή
    0.50
     Holes
    0.46
     লোহার
    0.46
     Gọi
    0.46
     fondamentali
    0.45
     controllo
    0.45
    া
    0.44
     사용하는
    0.44
     পাথর
    0.44
    POSITIVE LOGITS
    g
    0.55
    fps
    0.52
    c
    0.51
    q
    0.51
    y
    0.50
    ks
    0.48
    oint
    0.47
    experts
    0.47
    kg
    0.46
    peng
    0.46
    Activations Density 0.000%

    No Known Activations