© 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. 106906
    Prev
    Next
    INDEX
    Explanations

    geographic intersection of roads

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

    social media comparison

    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
    D
    0.58
    LIE
    0.50
    ש
    0.49
    W
    0.48
    NEXT
    0.47
    LN
    0.47
    V
    0.47
    OFF
    0.46
    NAN
    0.46
    Д
    0.46
    POSITIVE LOGITS
     आने
    0.52
    фесси
    0.50
     Haver
    0.49
     fleks
    0.47
     सीख
    0.46
     लाने
    0.46
     angla
    0.46
    能够
    0.45
     Comics
    0.45
     comedians
    0.45
    Activations Density 0.000%

    No Known Activations