© 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. 4572
    Prev
    Next
    INDEX
    Explanations

    code function prefixes

    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
     lies
    2.52
     denotes
    2.51
    )=-
    2.41
     holes
    2.36
    )=
    2.34
    =[],
    2.32
     score
    2.31
     virtues
    2.31
    =-
    2.29
     boundary
    2.27
    POSITIVE LOGITS
     stwor
    1.02
     costruzione
    1.01
    itetty
    1.01
     comerci
    0.97
    anfaatkan
    0.95
     çalışmalar
    0.92
    utip
    0.88
     jednom
    0.88
     encargado
    0.88
     ricost
    0.88
    Activations Density 0.001%

    No Known Activations