© 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. 15-GEMMASCOPE-2-RES-16K
    7. 5560
    Prev
    Next
    INDEX
    Explanations

    common prefixes

    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
    interpretation
    2.18
    agents
    2.14
    taxonomy
    2.12
    structure
    2.12
    cnf
    2.09
     descripcion
    2.07
    🙂
    2.05
    ={`
    2.05
     societ
    2.04
     saj
    2.01
    POSITIVE LOGITS
     UVB
    1.17
    زيد
    0.98
     Harlem
    0.97
    必ず
    0.93
    قلال
    0.92
    THON
    0.92
    ULONG
    0.91
    OSR
    0.90
    憚
    0.90
     Cret
    0.89
    Activations Density 0.003%

    No Known Activations