© 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. 144871
    Prev
    Next
    INDEX
    Explanations

    reviews, product quality, personal thoughts

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

    sales, technology, or uses

    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
    璐
    0.46
    OFFSET
    0.46
    ټبال
    0.44
    r
    0.44
    OnUiThread
    0.43
    Sprite
    0.43
    nThe
    0.42
     Resize
    0.42
    attaa
    0.41
    ่
    0.41
    POSITIVE LOGITS
     accepter
    0.52
     internes
    0.50
     نفسي
    0.49
    浚
    0.47
     Lü
    0.47
     Kemal
    0.47
     antes
    0.47
     себе
    0.47
     Benny
    0.47
     frío
    0.46
    Activations Density 0.001%

    No Known Activations