© 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. 57225
    Prev
    Next
    INDEX
    Explanations

    using the

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

    conflict, measurement, longing, exploration

    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
     نمبر
    0.46
     indicador
    0.44
    میری
    0.44
    权重
    0.42
    ього
    0.42
     saker
    0.42
    𝙷
    0.42
    激励
    0.41
     muda
    0.41
    Всім
    0.41
    POSITIVE LOGITS
     사용
    0.45
     the
    0.44
    handling
    0.44
     to
    0.43
    exe
    0.43
    ayt
    0.43
    venue
    0.42
    omb
    0.42
     耐
    0.42
     어려
    0.42
    Activations Density 0.000%

    No Known Activations