© 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. 58076
    Prev
    Next
    INDEX
    Explanations

    too old, overrating, has had

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

    how much

    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
     saben
    0.45
     schwarzen
    0.45
     እ
    0.44
     lentement
    0.43
     mangiare
    0.43
    にする
    0.42
     چال
    0.41
     jei
    0.40
     Dyed
    0.40
     đá
    0.39
    POSITIVE LOGITS
     आरोप
    0.45
    ಿಸಿದ್ದ
    0.44
     oftentimes
    0.44
     нередко
    0.44
     ஜனநாயக
    0.43
     fundamentally
    0.43
     तक्र
    0.43
    )}(
    0.42
    ecc
    0.41
     स्पर्धा
    0.41
    Activations Density 0.000%

    No Known Activations