© 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. 16-GEMMASCOPE-2-RES-262K
    7. 48959
    Prev
    Next
    INDEX
    Explanations

    code structure or data representation

    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_16_width_262k_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
    hato
    0.65
     Buku
    0.65
     Putra
    0.63
    자는
    0.61
    تری
    0.60
     Kathy
    0.60
    ra
    0.60
     Z
    0.60
    alur
    0.60
     오픈
    0.60
    POSITIVE LOGITS
     created
    0.59
     un
    0.57
     decre
    0.57
     remake
    0.57
     touching
    0.55
     nuanced
    0.55
     were
    0.54
     unsettling
    0.54
     nécess
    0.53
     menacing
    0.52
    Activations Density 0.026%

    No Known Activations