© 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. 60542
    Prev
    Next
    INDEX
    Explanations

    also consider and prepare

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

    answer access limitations

    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
    櫓
    0.51
    귿
    0.50
    চ
    0.49
    욬
    0.48
    DBGPRINT
    0.46
     publishers
    0.45
     বাঙ্গালীদের
    0.45
    μέ
    0.44
    谔
    0.44
     nikdy
    0.44
    POSITIVE LOGITS
    trou
    0.46
     &
    0.46
     desperate
    0.45
     
    0.45
     worsening
    0.45
     
    0.43
     •
    0.42
     Disaster
    0.42
     ~~
    0.42
    
    0.42
    Activations Density 0.000%

    No Known Activations