© 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. 22744
    Prev
    Next
    INDEX
    Explanations

    while back, almost completely, body types

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

    list items, bullet points

    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
    Neces
    0.54
    ־
    0.47
    Puede
    0.47
    Policy
    0.46
    Protocol
    0.45
    Funcion
    0.45
    赶紧
    0.45
    Benef
    0.44
    Automat
    0.44
     החד
    0.44
    POSITIVE LOGITS
     r
    0.47
     enkele
    0.46
     dois
    0.46
     às
    0.45
     myeloma
    0.45
     sizeof
    0.44
     methylene
    0.44
     eluted
    0.43
     circunferência
    0.43
     molasses
    0.43
    Activations Density 0.000%

    No Known Activations