© 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. 38104
    Prev
    Next
    INDEX
    Explanations

    politics and policy research institutes

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

    think tanks policy brief

    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
     rhinestone
    0.65
     deodor
    0.63
     motoc
    0.63
     jaunâtre
    0.61
     butyl
    0.60
     pigment
    0.59
     strawberry
    0.59
    莳
    0.59
     garante
    0.58
     neoprene
    0.57
    POSITIVE LOGITS
    political
    1.12
     politič
    1.11
     Brookings
    1.08
    政治
    1.06
     POLITICAL
    1.05
     полити
    1.04
     Political
    1.03
     political
    1.02
    Political
    1.02
     राजनीतिक
    1.00
    Activations Density 0.135%

    No Known Activations