© 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. 194607
    Prev
    Next
    INDEX
    Explanations

    bacteria and killing percentages

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

    sign-in email GB

    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
     addicts
    0.55
    }$&$-
    0.50
     被
    0.49
    લમાં
    0.49
    ្នក
    0.49
     devotees
    0.48
    的基本
    0.47
    錘
    0.47
    ચ્છ
    0.47
    రావు
    0.47
    POSITIVE LOGITS
    远
    0.47
    问
    0.42
    experimental
    0.41
     quang
    0.40
     یون
    0.40
    ization
    0.40
     altogether
    0.40
    *
    0.38
    وان
    0.38
     inundated
    0.38
    Activations Density 0.000%

    No Known Activations