© 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. 80022
    Prev
    Next
    INDEX
    Explanations

    specific nouns

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

    Updates and development challenges

    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
     ప్రో
    0.43
     nors
    0.42
    ulins
    0.42
     mik
    0.41
     hänen
    0.40
    룔
    0.40
     familiarize
    0.40
    注射
    0.40
    早
    0.38
     mids
    0.38
    POSITIVE LOGITS
    忤
    0.47
     ObjectID
    0.46
     Updating
    0.45
     दुष्प्रभाव
    0.45
     untenable
    0.45
    坞
    0.44
    彧
    0.44
     forcefully
    0.43
     Reject
    0.43
     objections
    0.42
    Activations Density 0.000%

    No Known Activations