© 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. 39482
    Prev
    Next
    INDEX
    Explanations

    ye, good, instead, which, but, heaven

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

    code blocks or formatted text

    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
    秚
    0.49
    籶
    0.46
    䉿
    0.44
    Businesses
    0.43
    仴
    0.43
     мяг
    0.42
     yaşında
    0.42
    ᓘ
    0.42
    ंत्रित
    0.41
    Falling
    0.41
    POSITIVE LOGITS
    it
    0.49
     a
    0.44
    ̀
    0.43
     say
    0.43
    બ
    0.41
    造
    0.41
    ᵃ
    0.41
     slander
    0.40
    갖
    0.40
     at
    0.40
    Activations Density 0.002%

    No Known Activations