© 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. 4376
    Prev
    Next
    INDEX
    Explanations

    words after punctuation

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

    cat grooming or qualifications

    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
    seudo
    0.47
     lava
    0.45
     quadr
    0.44
     crée
    0.44
     fordi
    0.42
    :
    0.42
    ̶
    0.41
    Creators
    0.41
     creators
    0.41
     Wade
    0.40
    POSITIVE LOGITS
     totalled
    0.45
    めている
    0.41
     বিধান
    0.41
     ;\
    0.41
     Staying
    0.40
     estimated
    0.40
     ત્યારબાદ
    0.39
    мента
    0.39
     \%$.
    0.38
    <unused12>
    0.38
    Activations Density 0.001%

    No Known Activations