© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 164187
    Prev
    Next
    INDEX
    Explanations

    available information

    np_acts-logits-general · gemini-2.5-flash-lite

    thank you for appreciate your

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    0.58
    <0x0D>
    0.51
     and
    0.51
    是
    0.49
    ong
    0.48
    IVATE
    0.48
    l
    0.48
    ić
    0.48
    是要
    0.48
    r
    0.48
    POSITIVE LOGITS
     धमाकेदार
    0.47
    Bray
    0.46
     بڑی
    0.45
     unbeatable
    0.44
     incineration
    0.44
     Cenomanian
    0.43
     اکبر
    0.43
     یق
    0.43
     SBT
    0.43
     बेहतरीन
    0.42
    Activations Density 0.001%

    No Known Activations