© 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. 41476
    Prev
    Next
    INDEX
    Explanations

    numbers and languages

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

    adjective followed by noun

    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
    नंतर
    0.48
     அவசியம்
    0.48
     Begriffe
    0.48
     फाय
    0.47
     subconscious
    0.46
    Ფ
    0.46
    likelihood
    0.46
    மிக
    0.46
     मूर्त
    0.46
    ⦕
    0.45
    POSITIVE LOGITS
     nueve
    0.54
     six
    0.48
     Frederick
    0.45
     Williamsburg
    0.44
     seis
    0.43
     Mardi
    0.42
     y
    0.42
     avec
    0.42
     nine
    0.42
     nebo
    0.42
    Activations Density 0.000%

    No Known Activations