© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5139
    Prev
    Next
    INDEX
    Explanations

    command prompt

    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_15_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
     kola
    1.49
     oči
    1.49
    Fuente
    1.43
    ümüş
    1.42
    玻
    1.42
     rouge
    1.41
     distribución
    1.41
    Reporting
    1.41
     corsa
    1.39
    statuses
    1.39
    POSITIVE LOGITS
    侩
    0.93
     మేరకు
    0.91
     أهم
    0.91
     avvic
    0.88
    MPT
    0.87
     deleg
    0.84
    มาย
    0.84
    çin
    0.83
    торое
    0.83
     disconnecting
    0.83
    Activations Density 0.035%

    No Known Activations