© 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. 84517
    Prev
    Next
    INDEX
    Explanations

    vectorization, matrix transformations

    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
     Donation
    0.47
    ifu
    0.46
     Fundraising
    0.45
    -
    0.45
    OME
    0.45
     fundraising
    0.43
    EX
    0.42
    专
    0.42
     Decoding
    0.42
    TV
    0.42
    POSITIVE LOGITS
     protagonisti
    0.49
    ни
    0.49
     entertained
    0.46
     rédu
    0.46
     résist
    0.46
     hoisted
    0.46
     strolled
    0.45
     resistive
    0.45
     afresh
    0.45
     theſe
    0.45
    Activations Density 0.003%

    No Known Activations