© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 10936
    Prev
    Next
    INDEX
    Explanations

    rule out any, policies are

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    
    1.82
    殘
    1.67
    ,/*
    1.66
    검
    1.65
    ͇
    1.63
    бия
    1.62
    篒
    1.59
    
    1.58
    коми
    1.56
    狧
    1.56
    POSITIVE LOGITS
     of
    1.19
     rep
    1.13
     converging
    1.10
     R
    1.10
     E
    1.09
     robot
    1.09
     ort
    1.08
     organic
    1.08
     rally
    1.07
     park
    1.07
    Activations Density 0.000%

    No Known Activations