© 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. 5854
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts

    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
     thence
    1.09
    ravés
    0.87
     dále
    0.81
    :-
    0.76
     Warrant
    0.73
    wards
    0.71
    torrent
    0.70
    
    0.70
    thon
    0.70
     exact
    0.69
    POSITIVE LOGITS
    лой
    1.89
     Selena
    1.82
    קל
    1.81
     Boise
    1.78
    diyl
    1.78
     multiplicative
    1.78
     adrenal
    1.78
     HSM
    1.74
    писи
    1.74
     greg
    1.73
    Activations Density 0.044%

    No Known Activations