© 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. 72526
    Prev
    Next
    INDEX
    Explanations

    emerging nuclearfirst forayhad workcomplete yourPractices implicationsIs under

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

    identifying quality variations

    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
    ي
    0.54
     bistouri
    0.52
     irritate
    0.50
    י
    0.49
    iodate
    0.49
     Maugin
    0.48
     perdu
    0.47
    ないので
    0.46
     provoque
    0.46
    irai
    0.46
    POSITIVE LOGITS
     Electro
    0.47
     Supplementary
    0.47
    ᴏ
    0.47
     Diverse
    0.46
     அமைச்சர்
    0.45
     Gas
    0.45
     जीता
    0.44
     Stadium
    0.44
     Uni
    0.44
     Suburban
    0.44
    Activations Density 0.001%

    No Known Activations