© 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. 7500
    Prev
    Next
    INDEX
    Explanations

    code comments or documentation

    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
     تای
    1.30
     kỷ
    1.17
     thứ
    1.16
     +\
    1.15
    icuous
    1.14
    vió
    1.12
    gete
    1.10
     :=\
    1.07
     có
    1.06
    agian
    1.06
    POSITIVE LOGITS
    <code>
    2.03
     moduli
    2.02
    embedding
    1.98
     Casablanca
    1.98
     Cortes
    1.95
     Gonzales
    1.94
    oui
    1.91
     Representations
    1.89
     Mahoney
    1.88
     Madera
    1.88
    Activations Density 0.001%

    No Known Activations