© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 15663
    Prev
    Next
    INDEX
    Explanations

    past, guest, adding, buses

    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_65k_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
    Optimal
    0.42
     Optimal
    0.40
    Kansas
    0.40
     👀
    0.39
     Genn
    0.38
    ")]
    0.38
     alias
    0.37
     ópt
    0.37
    ]^
    0.37
    િન
    0.37
    POSITIVE LOGITS
     ()=>{
    0.51
    numberOfRecords
    0.47
    uki
    0.46
    да
    0.46
    உலக
    0.46
     ponerse
    0.45
    ເຮັດ
    0.43
    艐
    0.43
     tume
    0.43
    ulong
    0.43
    Activations Density 0.001%

    No Known Activations