© 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. 65041
    Prev
    Next
    INDEX
    Explanations

    living on the park

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

    DJ sets

    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
    union
    0.45
    i
    0.44
    apol
    0.44
     substance
    0.43
    outgoing
    0.42
    ல
    0.42
    industrial
    0.41
    ’
    0.41
    il
    0.41
    and
    0.41
    POSITIVE LOGITS
     longiore
    0.56
     kleinere
    0.56
     errado
    0.51
    েমনি
    0.50
    كبر
    0.50
    鯢
    0.50
    훑
    0.50
     dined
    0.49
     Smaller
    0.48
     scouts
    0.48
    Activations Density 0.000%

    No Known Activations