© 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. 6108
    Prev
    Next
    INDEX
    Explanations

    museums and universities

    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
    mason
    1.63
     fudge
    1.59
     dennoch
    1.57
     Greeley
    1.56
    éhez
    1.55
    <unused272>
    1.51
     Meade
    1.51
     chadd
    1.49
     Fremont
    1.48
     Coolidge
    1.46
    POSITIVE LOGITS
     Firma
    1.47
     „
    1.41
     Técnico
    1.40
     Postgraduate
    1.35
     Polite
    1.35
     Coordination
    1.32
     «
    1.29
     specialization
    1.28
     specialists
    1.26
     Specialist
    1.26
    Activations Density 0.209%

    No Known Activations