© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 40185
    Prev
    Next
    INDEX
    Explanations

    people are, on lake, can tell, were battling

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

    mathematical operations and locations

    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
     প্লে
    0.54
     पॉलिसी
    0.52
    |^{-
    0.51
    >(
    0.51
     litros
    0.49
    obac
    0.49
     reallocation
    0.47
    >/
    0.46
    ไม่ต้อง
    0.46
     precisar
    0.45
    POSITIVE LOGITS
     fiery
    0.46
    то
    0.45
     weihn
    0.44
    ),
    0.43
     direzione
    0.43
    7
    0.43
    army
    0.43
    9
    0.43
    entre
    0.41
    தேச
    0.41
    Activations Density 0.000%

    No Known Activations