© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 155133
    Prev
    Next
    INDEX
    Explanations

    survival, agreements, those, beer, list, ratio, contact, save, refer

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

    mimic, forget, time, attempting

    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
     suscept
    0.55
    殇
    0.54
     டிகிரி
    0.49
     Дон
    0.49
     уйнау
    0.49
     그리고
    0.48
     باسکٹ
    0.48
    atanga
    0.48
    CEPTION
    0.48
     неприят
    0.47
    POSITIVE LOGITS
     
    0.56
     works
    0.50
    </strong>
    0.49
     Ech
    0.47
     hairstyles
    0.46
     Tribes
    0.46
     Globes
    0.46
     rituals
    0.45
     artworks
    0.45
     offers
    0.45
    Activations Density 0.000%

    No Known Activations