© 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. 173674
    Prev
    Next
    INDEX
    Explanations

    oil pump

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

    where questions lead

    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
    le
    0.44
    matic
    0.42
    ð
    0.42
     inconvenience
    0.41
    chomp
    0.41
     thermally
    0.41
    rom
    0.41
    ussels
    0.41
    lem
    0.40
    ism
    0.40
    POSITIVE LOGITS
     AGAIN
    0.55
     항
    0.49
     为
    0.49
     것으로
    0.49
    ALPHA
    0.48
     최초
    0.47
     특정
    0.47
     AGRE
    0.46
     THAN
    0.46
     বৈঠকে
    0.46
    Activations Density 0.001%

    No Known Activations