© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 2050
    Prev
    Next
    INDEX
    Explanations

    resource links and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     વિચ
    0.83
     too
    0.79
     constructor
    0.79
     constructors
    0.76
     TOO
    0.75
    맣
    0.74
     ReactNative
    0.70
     מער
    0.68
     عندك
    0.68
     Too
    0.68
    POSITIVE LOGITS
     citation
    1.13
    Citation
    1.02
     cite
    1.00
    citation
    0.96
     footnote
    0.96
    </sup>
    0.95
    Cite
    0.93
    cite
    0.92
    †
    0.91
     citations
    0.85
    Activations Density 0.054%

    No Known Activations