© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 204754
    Prev
    Next
    INDEX
    Explanations

    concepts followed by related nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ŝ
    0.48
    forc
    0.48
    portivo
    0.47
    橢
    0.46
     جمہوری
    0.46
    llä
    0.45
     utilizzare
    0.44
    ļ
    0.44
     faible
    0.44
    эффици
    0.43
    POSITIVE LOGITS
     Hilton
    0.46
     Almond
    0.45
     Kurdistan
    0.43
     Tammy
    0.43
     Alamo
    0.41
     Alsace
    0.41
     আগস্ট
    0.40
     Bahamas
    0.40
     Walnut
    0.40
     Allegheny
    0.40
    Activations Density 0.006%

    No Known Activations