© 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. 174630
    Prev
    Next
    INDEX
    Explanations

    academic degrees and completion

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

    Degree of, atom nanozymes

    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
    óri
    0.45
    ５
    0.45
    ７
    0.44
     przeciw
    0.43
    7
    0.41
    ４
    0.41
    dummy
    0.41
     recour
    0.41
     বিক
    0.40
    ８
    0.40
    POSITIVE LOGITS
     Refunds
    0.50
     Hala
    0.48
    ة
    0.46
     gelas
    0.46
     anges
    0.46
    变化的
    0.45
     bords
    0.43
    债券
    0.43
     ModInt
    0.43
     рамках
    0.43
    Activations Density 0.001%

    No Known Activations