© 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. 120968
    Prev
    Next
    INDEX
    Explanations

    group names followed by related entities

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

    resorts, nurse, neutron

    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
    OnHand
    0.49
     зміни
    0.48
     ಮಾ
    0.47
     Це
    0.45
     юриди
    0.44
     организа
    0.44
    Catholic
    0.44
    >′</
    0.44
     канторы
    0.44
    等於
    0.44
    POSITIVE LOGITS
     agak
    0.47
    로
    0.45
     Circulation
    0.42
     neutron
    0.42
    5
    0.40
    这
    0.40
     vor
    0.40
     aplica
    0.39
     penetrated
    0.39
    op
    0.39
    Activations Density 0.002%

    No Known Activations