© 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. 99886
    Prev
    Next
    INDEX
    Explanations

    journalists

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

    discrete packets or chunks

    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
    肉
    0.47
     classement
    0.45
     Moyen
    0.45
     Regel
    0.44
     Schedules
    0.44
     Université
    0.44
     Corpus
    0.44
    口感
    0.44
     Scenario
    0.43
    既
    0.43
    POSITIVE LOGITS
     flyers
    0.55
    hiti
    0.53
     journalists
    0.52
     buttons
    0.50
     magnification
    0.50
     antlers
    0.49
     पत्रकार
    0.47
    ca
    0.47
     monarchs
    0.47
    ">'+
    0.47
    Activations Density 0.002%

    No Known Activations