© 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. 3814
    Prev
    Next
    INDEX
    Explanations

    witnessing and interacting

    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
    atuan
    1.91
    溜
    1.89
     beant
    1.85
     resultante
    1.84
     تتم
    1.84
     minimalism
    1.83
     compulsive
    1.82
     codified
    1.80
     งวด
    1.80
    缴
    1.79
    POSITIVE LOGITS
     eğit
    0.86
    intermedi
    0.85
    touch
    0.82
     çalışt
    0.82
     contatt
    0.81
    Profiling
    0.80
     دیدار
    0.79
     surve
    0.79
     entreten
    0.77
     beraten
    0.76
    Activations Density 0.393%

    No Known Activations