© 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. 7652
    Prev
    Next
    INDEX
    Explanations

    contextualizing nouns

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

    boundaries of domains

    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
    is
    0.60
    id
    0.52
    x
    0.51
     বাড়ির
    0.50
    ន្ថ
    0.49
    ની
    0.48
     বাড়িতে
    0.48
    q
    0.48
    ants
    0.48
     या
    0.47
    POSITIVE LOGITS
     permasalahan
    0.54
     mediocr
    0.54
     contexte
    0.53
     компетен
    0.53
     realm
    0.52
     extremism
    0.52
     traged
    0.50
    ForgotPassword
    0.49
     prostitution
    0.49
    nosti
    0.48
    Activations Density 0.114%

    No Known Activations