© 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. 13226
    Prev
    Next
    INDEX
    Explanations

    expresses preference

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

    preference or choice

    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
     a
    0.88
    a
    0.74
    א
    0.73
    اف
    0.72
     The
    0.68
     IOException
    0.66
    ה
    0.65
    ان
    0.64
    \
    0.64
    '}
    0.63
    POSITIVE LOGITS
    prefer
    1.07
     prefers
    1.05
     prefer
    1.02
     предпоч
    1.02
     предпочита
    1.02
     preferring
    0.99
    preferred
    0.95
    preference
    0.94
     preferred
    0.90
     preferable
    0.89
    Activations Density 0.026%

    No Known Activations