© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 47835
    Prev
    Next
    INDEX
    Explanations

    an [word]

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

    vowel-initial words

    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
    その
    0.64
    υ
    0.61
    يا
    0.57
    yaj
    0.57
    ೇವಿನ
    0.55
    UG
    0.54
    carbonate
    0.54
    ফ
    0.53
    䉽
    0.51
    γι
    0.51
    POSITIVE LOGITS
     an
    1.06
    swering
    0.87
    ä
    0.85
    achron
    0.80
     unforgettable
    0.80
     équipe
    0.77
     encyclopedia
    0.77
    xiety
    0.77
     illogical
    0.77
     intracranial
    0.76
    Activations Density 0.284%

    No Known Activations