© 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. 4727
    Prev
    Next
    INDEX
    Explanations

    it makes sense

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

    pronoun-verb contractions

    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
    、
    0.19
    ，
    0.17
    .,
    0.17
    ،
    0.17
    认为
    0.16
    ॒
    0.16
     ซึ่ง
    0.16
    、《
    0.15
     ,
    0.15
    Although
    0.15
    POSITIVE LOGITS
     stvarn
    0.19
     isn
    0.17
     really
    0.17
     brukes
    0.17
     veldig
    0.15
    OCKED
    0.15
     electricidad
    0.15
     இருக்கும்
    0.15
     nějak
    0.15
    ોર્ટ
    0.15
    Activations Density 0.503%

    No Known Activations