© 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. 74198
    Prev
    Next
    INDEX
    Explanations

    landslide, mechanic, marble, generator, station

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

    Jey Uso negotiations products

    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
     cognizant
    0.46
     numeracy
    0.41
    5
    0.41
     their
    0.41
     mentioned
    0.40
     knowledgeable
    0.39
     similarly
    0.39
     Appliance
    0.38
     Their
    0.38
     Wikimedia
    0.38
    POSITIVE LOGITS
    病人
    0.49
    ậc
    0.47
    就可以了
    0.46
    㷌
    0.45
    ளு
    0.44
    𝗎
    0.44
    ulte
    0.44
    只限平日
    0.44
    años
    0.44
    Funcion
    0.44
    Activations Density 0.002%

    No Known Activations