© 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. 4700
    Prev
    Next
    INDEX
    Explanations

    do my best

    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
    𝗄
    1.32
     Confederacy
    1.27
     diseases
    1.25
    Bran
    1.24
    anzia
    1.23
    ensburg
    1.23
     apnea
    1.22
    Equation
    1.18
    acchus
    1.17
    솟
    1.14
    POSITIVE LOGITS
     wholeheartedly
    1.69
     cordial
    1.56
     sincere
    1.56
    梶
    1.55
    全力
    1.49
     sincer
    1.48
    łożyć
    1.44
    йдет
    1.43
    topo
    1.41
     wrześ
    1.40
    Activations Density 0.195%

    No Known Activations