© 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. 12-GEMMASCOPE-2-RES-16K
    7. 4038
    Prev
    Next
    INDEX
    Explanations

    explains shell script execution

    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_12_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
     everyone
    1.67
     people
    1.55
    .
    1.54
     everybody
    1.51
    洙
    1.50
     acela
    1.49
     namanya
    1.47
     one
    1.45
     unanimous
    1.45
     the
    1.44
    POSITIVE LOGITS
     %>',
    2.01
    ᱛ
    1.98
    Config
    1.91
    علم
    1.87
    ൯
    1.86
    ᱠ
    1.84
     CDN
    1.82
    Utils
    1.82
    ɢ
    1.79
    bouncer
    1.78
    Activations Density 0.000%

    No Known Activations