© 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-262K
    7. 78805
    Prev
    Next
    INDEX
    Explanations

    less than 10 years

    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_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
    לות
    0.46
    λώ
    0.45
     giusto
    0.43
     reclama
    0.43
    ৌম
    0.43
    ﮐ
    0.42
     comunica
    0.41
     podían
    0.40
    本来
    0.39
    愀
    0.39
    POSITIVE LOGITS
    s
    0.51
    cure
    0.47
    anian
    0.45
     классов
    0.44
    izzeria
    0.43
     рациона
    0.43
    人を
    0.42
     घ
    0.42
     كم
    0.42
     위해서는
    0.41
    Activations Density 0.001%

    No Known Activations