© 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. 2843
    Prev
    Next
    INDEX
    Explanations

    LaTeX package inclusions and code structures

    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
     cmds
    1.40
    tır
    1.37
    ERGY
    1.33
    GraphicsUnit
    1.33
    ónimo
    1.31
    inci
    1.31
    scrire
    1.30
    \|+\
    1.30
    ernum
    1.30
    IRCONIUM
    1.30
    POSITIVE LOGITS
    End
    1.24
     further
    1.10
     reboot
    1.09
     Kamen
    1.09
    τικ
    1.05
    further
    1.05
    end
    1.04
    Wend
    1.03
     farther
    1.02
     stup
    1.01
    Activations Density 0.006%

    No Known Activations