© 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. 115677
    Prev
    Next
    INDEX
    Explanations

    earplugs or heart failure

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

    asking if you want to hear

    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
    h
    0.61
    daki
    0.49
    ，
    0.47
     Vign
    0.46
    1
    0.46
    3
    0.46
    2
    0.44
     Kennedy
    0.44
     ،
    0.43
    5
    0.43
    POSITIVE LOGITS
    ulfanyl
    0.49
     altered
    0.47
    쭈
    0.44
    新たな
    0.44
    高的
    0.43
     voids
    0.42
    setType
    0.42
    fstream
    0.42
     unaltered
    0.42
     दिलाया
    0.41
    Activations Density 0.001%

    No Known Activations