© 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. 2253
    Prev
    Next
    INDEX
    Explanations

    common function descriptions

    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
    izdat
    1.31
    ethoscope
    1.28
    աք
    1.27
    Ordine
    1.27
     refineries
    1.27
    etiti
    1.26
     immunoprec
    1.26
    廷
    1.25
    éfonos
    1.24
    dding
    1.24
    POSITIVE LOGITS
    pire
    1.01
    LT
    0.97
     distX
    0.96
    lcc
    0.90
     largos
    0.90
    <0x92>
    0.88
     totales
    0.88
    킵
    0.87
    VG
    0.85
    ボリー
    0.85
    Activations Density 0.120%

    No Known Activations