© 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. 5110
    Prev
    Next
    INDEX
    Explanations

    opening files with open

    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
     μπο
    1.18
    榨
    1.11
     Passed
    1.06
     DWORD
    1.05
     hará
    1.01
     Pressed
    1.01
     evac
    1.00
     kiezen
    0.99
     Verfü
    0.99
     entschieden
    0.98
    POSITIVE LOGITS
    citep
    1.52
    prefix
    1.51
    шое
    1.51
     veterinarians
    1.47
    artifactId
    1.46
    锚
    1.34
     sulfates
    1.32
    彦
    1.30
    citet
    1.30
    сан
    1.29
    Activations Density 0.011%

    No Known Activations