© 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. 22494
    Prev
    Next
    INDEX
    Explanations

    words starting with W

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

    words starting with w

    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
    u
    1.06
    ش
    1.00
    that
    0.96
    ant
    0.84
    ova
    0.78
    ado
    0.76
    తో
    0.73
    ют
    0.72
    were
    0.72
     that
    0.70
    POSITIVE LOGITS
    ژگی
    0.91
    W
    0.84
    性と
    0.82
     ແລະ
    0.79
    AY
    0.79
     wonderful
    0.79
    ля
    0.76
    CH
    0.76
    ্ল্ড
    0.75
    ે
    0.74
    Activations Density 0.439%

    No Known Activations