© 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. 4794
    Prev
    Next
    INDEX
    Explanations

    Java unit tests

    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
     pensions
    1.56
    quoise
    1.51
     pension
    1.46
     Pension
    1.40
    닳
    1.30
    Pension
    1.29
     solvency
    1.29
     Pensions
    1.26
     Lill
    1.26
     Cardiol
    1.25
    POSITIVE LOGITS
    veld
    1.91
     Salisbury
    1.79
     Worcestershire
    1.78
    批量
    1.76
     σειρά
    1.76
     silvest
    1.76
     maad
    1.74
    𝘇
    1.72
     thok
    1.72
     doubleheader
    1.71
    Activations Density 0.000%

    No Known Activations