© 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. 190140
    Prev
    Next
    INDEX
    Explanations

    foreign or non-english words

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

    flags, wire, nationalism, genes, personality, relationship, targeted, Platonism

    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
     Krankenhaus
    0.53
    残念
    0.48
    ين
    0.48
    人形
    0.47
    開封
    0.46
     jahr
    0.44
    頃
    0.43
    競技
    0.43
    ての
    0.43
    崧
    0.43
    POSITIVE LOGITS
    ião
    0.57
     требует
    0.50
    ică
    0.50
    iça
    0.49
    është
    0.48
    çon
    0.47
    ńca
    0.46
     टाई
    0.46
    ulé
    0.45
     त्यावर
    0.44
    Activations Density 0.000%

    No Known Activations