© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 31080
    Prev
    Next
    INDEX
    Explanations

    initiating explanations of "what is"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     pressure
    0.55
     presión
    0.53
    )\
    0.52
     but
    0.51
     push
    0.51
     hyperbolic
    0.46
     [\
    0.45
     cuz
    0.45
     comentario
    0.45
     BUT
    0.44
    POSITIVE LOGITS
    手術
    0.59
    ílio
    0.49
    ">+
    0.48
    esseract
    0.46
    saldo
    0.46
    备份
    0.45
    ale
    0.45
     μεγ
    0.44
    rett
    0.44
    手术
    0.44
    Activations Density 0.002%

    No Known Activations