© 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. 122071
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and nouns

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

    following certain 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
     लेकिन
    0.39
    ধান
    0.38
     مانند
    0.38
     Sometimes
    0.38
     nowadays
    0.37
     También
    0.37
     pursued
    0.36
    <unused2148>
    0.36
    妓
    0.35
     Nowadays
    0.35
    POSITIVE LOGITS
    нном
    0.45
    您的
    0.44
    믈
    0.43
     ваш
    0.41
    你的
    0.41
     их
    0.40
     votre
    0.40
     workpiece
    0.40
     কর্তৃ
    0.39
     அவர்களுடைய
    0.39
    Activations Density 0.005%

    No Known Activations