© 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. 1140
    Prev
    Next
    INDEX
    Explanations

    home improvement, tech accessories

    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
     debacle
    0.89
     culminating
    0.83
     zależ
    0.80
     provenant
    0.78
     …
    0.77
     discursive
    0.73
     sämt
    0.72
     proverbial
    0.71
     deliberations
    0.71
     alluded
    0.71
    POSITIVE LOGITS
     exquisite
    1.42
     ，
    1.35
    Suitable
    1.24
     exquis
    1.22
     、
    1.21
     】
    1.19
    【
    1.19
     Suitable
    1.18
    ￩
    1.17
    pcs
    1.16
    Activations Density 0.480%

    No Known Activations