© 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. 30716
    Prev
    Next
    INDEX
    Explanations

    LaTeX templates and styles

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

    LaTeX format

    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
     USB
    0.51
     americ
    0.51
    "
    0.50
     workman
    0.49
     EEUU
    0.48
    <0x0D>
    0.47
     projective
    0.46
     cinese
    0.46
     unbalanced
    0.45
     DM
    0.45
    POSITIVE LOGITS
    ponenten
    0.59
    𝐬
    0.56
    inoceros
    0.54
    Cs
    0.53
    istet
    0.52
    sini
    0.52
    皰
    0.52
    ر
    0.51
    حب
    0.51
    Os
    0.50
    Activations Density 0.000%

    No Known Activations