© 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-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3978
    Prev
    Next
    INDEX
    Explanations

    formal phrasing and transformations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ्याज
    0.91
     Lonely
    0.84
     soprano
    0.84
    ᑎ
    0.83
     不是
    0.81
    ᕝ
    0.81
     escritor
    0.80
     chibi
    0.80
    ᓂ
    0.79
     Caffeine
    0.78
    POSITIVE LOGITS
     Moreover
    0.78
     …
    0.78
     Furthermore
    0.77
    ...”
    0.76
    ].”
    0.73
    ...
    0.73
     [
    0.73
     [...]
    0.72
     می‌کنند
    0.72
    …
    0.71
    Activations Density 0.955%

    No Known Activations