© 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. 224742
    Prev
    Next
    INDEX
    Explanations

    sport horses. business. thanks. congrats. partner

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

    setting and genre

    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
    AssetDiscovery
    0.55
     ម
    0.53
     коллеги
    0.51
     внутри
    0.51
     stripe
    0.50
     подар
    0.49
    ক্রে
    0.49
     кроме
    0.49
    Кроме
    0.49
    
    0.49
    POSITIVE LOGITS
    sust
    0.48
    sport
    0.47
    iences
    0.47
    tts
    0.46
    ticks
    0.45
    tus
    0.44
    shit
    0.43
    pots
    0.43
     Mapping
    0.43
    sky
    0.43
    Activations Density 0.000%

    No Known Activations