© 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. 154665
    Prev
    Next
    INDEX
    Explanations

    locations and names

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

    vaporwave

    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
     ফুলের
    0.53
     cutt
    0.50
    
    0.48
     Spe
    0.47
     चढ
    0.47
     taglio
    0.46
     mouve
    0.46
     mů
    0.46
    cutoff
    0.46
     لوبی
    0.46
    POSITIVE LOGITS
     implementation
    0.51
    JER
    0.47
    BC
    0.46
     contaminated
    0.44
    arna
    0.43
    J
    0.42
    pH
    0.42
    implementation
    0.42
    }!
    0.42
    这段
    0.41
    Activations Density 0.001%

    No Known Activations