© 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. 42905
    Prev
    Next
    INDEX
    Explanations

    posted dates

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

    science and data extraction

    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
    문화
    0.53
    传媒
    0.53
    诞生
    0.51
    谋
    0.50
    Tourism
    0.49
    Advertising
    0.49
    创作
    0.48
    鸦
    0.48
    City
    0.48
     Visitation
    0.48
    POSITIVE LOGITS
     molecules
    0.78
     molecule
    0.74
     proteins
    0.73
     moléculas
    0.72
     atoms
    0.70
     protein
    0.70
     spectra
    0.67
     photons
    0.66
     phonons
    0.66
     enzym
    0.66
    Activations Density 0.000%

    No Known Activations