© 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. 70778
    Prev
    Next
    INDEX
    Explanations

    possessive pronoun then noun

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

    starts with "Born" or "developed"

    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
    沒
    0.50
    বাদের
    0.49
    ד
    0.49
    ❿
    0.47
    чено
    0.46
    קו
    0.46
    けない
    0.46
    וד
    0.46
    ኻ
    0.46
    ような
    0.45
    POSITIVE LOGITS
     Emper
    0.46
     глав
    0.45
    a
    0.45
     It
    0.43
    ្ស
    0.42
    兖
    0.42
     Embedded
    0.41
     Aryan
    0.41
     Enterprise
    0.41
     Aydın
    0.41
    Activations Density 0.001%

    No Known Activations