© 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. 201010
    Prev
    Next
    INDEX
    Explanations

    photodiode, photons, photo-conductive

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

    technical communication 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
     Orion
    0.44
     sorted
    0.43
     pard
    0.43
    Kristen
    0.43
    :,
    0.42
    යා
    0.42
     Judi
    0.42
     namun
    0.41
     கிருஷ்
    0.41
     তবুও
    0.41
    POSITIVE LOGITS
    संच
    0.46
     sowing
    0.45
     ಸ
    0.44
    vering
    0.44
    amol
    0.44
    undaki
    0.44
    𝘂
    0.44
    рів
    0.43
    啄
    0.43
    𝗰
    0.43
    Activations Density 0.000%

    No Known Activations