© 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. 12-GEMMASCOPE-2-RES-16K
    7. 7166
    Prev
    Next
    INDEX
    Explanations

    S.M.A.R.T. and S.O.L.I.D. principles

    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_12_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
    amard
    1.24
     probado
    1.20
    ónicas
    1.12
     perut
    1.11
    佢
    1.10
     conspiracy
    1.07
    izos
    1.06
     desmont
    1.05
    燙
    1.03
    atres
    1.03
    POSITIVE LOGITS
     Focus
    2.14
    Applic
    2.02
     Monterey
    1.94
     насто
    1.93
     Palm
    1.93
     Kiran
    1.84
     Slov
    1.84
     Papua
    1.82
     Sprint
    1.81
     Intell
    1.81
    Activations Density 0.001%

    No Known Activations