© 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. 47057
    Prev
    Next
    INDEX
    Explanations

    its durability

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

    better after punctuation

    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
    >′</
    0.52
    ieważ
    0.52
    gtr
    0.51
    ехала
    0.50
     पुराना
    0.49
    requested
    0.49
    nać
    0.46
    yana
    0.46
    upe
    0.45
    поте
    0.44
    POSITIVE LOGITS
    喋
    0.49
    ือง
    0.47
     quirks
    0.44
     kaut
    0.43
     enrollment
    0.42
     analyzing
    0.41
     Quir
    0.41
     ہیں۔
    0.41
     teaming
    0.41
    逗
    0.41
    Activations Density 0.000%

    No Known Activations