© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3623
    Prev
    Next
    INDEX
    Explanations

    adjectives or descriptors

    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
     this
    0.94
    这个
    0.92
    有着
    0.85
    "
    0.85
     ought
    0.84
     these
    0.84
    的时候
    0.83
     an
    0.83
     thing
    0.82
     twenty
    0.80
    POSITIVE LOGITS
     Yes
    1.17
    Yes
    1.05
     $+$
    1.02
     Usually
    1.00
     Mostly
    0.99
     +,
    0.98
     +
    0.96
     Mainly
    0.91
    Usually
    0.91
     Avg
    0.91
    Activations Density 0.201%

    No Known Activations