© 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. 144773
    Prev
    Next
    INDEX
    Explanations

    PEFT

    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
    ین
    1.19
    𝗚
    0.92
    ੋ
    0.91
    ENT
    0.86
     médicos
    0.84
    すべての
    0.82
     inquis
    0.82
    ेप
    0.80
     interwoven
    0.80
    グ
    0.80
    POSITIVE LOGITS
     PE
    1.73
     pe
    1.68
    ي
    1.65
    Pe
    1.60
    ן
    1.59
     Pe
    1.55
    h
    1.45
    لي
    1.36
    ри
    1.34
    pe
    1.24
    Activations Density 0.004%

    No Known Activations