© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 44775
    Prev
    Next
    INDEX
    Explanations

    image

    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
    nt
    0.51
    down
    0.46
    d
    0.46
    te
    0.45
    um
    0.44
    ra
    0.43
    don
    0.43
    mente
    0.43
    illiams
    0.43
     defenseman
    0.43
    POSITIVE LOGITS
     FabD
    0.47
    ية
    0.47
    佅
    0.47
     inactivació
    0.47
     Bourd
    0.46
    <unused1089>
    0.46
     impairs
    0.46
     subsidies
    0.46
     الطب
    0.45
     आले
    0.45
    Activations Density 0.000%

    No Known Activations