© 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. 815
    Prev
    Next
    INDEX
    Explanations

    cannot provide

    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
     Rg
    0.90
     ND
    0.78
    мони
    0.78
    嵘
    0.74
     RDF
    0.73
     MTL
    0.70
     RD
    0.70
     ICD
    0.70
     BMS
    0.70
     OCPP
    0.69
    POSITIVE LOGITS
     Perez
    1.00
    daa
    0.94
    ========
    0.94
    =====
    0.93
     Connelly
    0.91
     Halsey
    0.90
     Cox
    0.89
    Bren
    0.89
    Corre
    0.88
     Brennan
    0.88
    Activations Density 2.907%

    No Known Activations