© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5726
    Prev
    Next
    INDEX
    Explanations

    "and" followed by abstract nouns of progress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
    īgi
    0.98
     Indem
    0.95
    
    0.91
    兼
    0.85
     Toxicol
    0.84
     *}$
    0.84
     Taunton
    0.84
     wszyst
    0.84
    </li>
    0.81
    缀
    0.80
    POSITIVE LOGITS
    ADB
    1.79
    йда
    1.73
    hanna
    1.62
    เมริกา
    1.60
     legitimacy
    1.60
     contraction
    1.59
     breakout
    1.57
     development
    1.56
    DATABASE
    1.54
    VariableName
    1.54
    Activations Density 0.062%

    No Known Activations