© 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. 64897
    Prev
    Next
    INDEX
    Explanations

    tend to

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

    tendency and inclination

    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
    ุ
    0.69
    ะ
    0.67
    s
    0.66
    ן
    0.66
     an
    0.66
    ни
    0.63
    age
    0.63
    an
    0.62
    ی
    0.61
    ের
    0.61
    POSITIVE LOGITS
     tend
    1.08
    倾向
    1.08
     tendency
    1.05
     tende
    1.02
     tendencia
    1.00
     тенден
    0.99
    傾向
    0.99
     tends
    0.98
    Tend
    0.98
     tendencies
    0.96
    Activations Density 0.028%

    No Known Activations