© 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. 112458
    Prev
    Next
    INDEX
    Explanations

    The or a

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

    showing contrast or condition

    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
    मह
    0.52
    तां
    0.51
    ु
    0.49
     ہیں۔
    0.48
    滿足
    0.48
    बान
    0.46
    ズノ
    0.46
    庄
    0.46
    瑪
    0.46
    ρούν
    0.45
    POSITIVE LOGITS
     imagining
    0.46
     امید
    0.44
     অবি
    0.44
     brightest
    0.44
     imagination
    0.43
    ointe
    0.43
    ouse
    0.43
    ych
    0.42
    jell
    0.42
     ան
    0.42
    Activations Density 0.000%

    No Known Activations