© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 181329
    Prev
    Next
    INDEX
    Explanations

    properly or minimize

    np_acts-logits-general · gemini-2.5-flash-lite

    within [measurement/time]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ل
    0.46
     لله
    0.43
     cellule
    0.42
    単位
    0.42
    их
    0.42
     wasteful
    0.42
     dismal
    0.41
    খী
    0.41
    ൬
    0.41
     bipartite
    0.41
    POSITIVE LOGITS
    yer
    0.49
     Tvam
    0.47
     Nearby
    0.46
    `/
    0.45
    )，
    0.44
    `-
    0.44
    ৫৮
    0.44
    tober
    0.43
     />
    0.43
    >`
    0.43
    Activations Density 0.000%

    No Known Activations