© 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. 84922
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

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

    counter narrative, IT Admin, project SAVE

    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
    𝖽
    0.44
     ZOOM
    0.42
     اخذنا
    0.38
    汥
    0.38
    批准
    0.38
    cPix
    0.38
    也都
    0.38
    曳
    0.37
    糠
    0.37
    timelist
    0.36
    POSITIVE LOGITS
     моих
    0.52
     मेरी
    0.49
     patru
    0.49
     mein
    0.47
     tentang
    0.47
    เกี่ยวกับ
    0.46
     मुझ
    0.46
     मेरा
    0.45
     acht
    0.45
     moje
    0.45
    Activations Density 0.007%

    No Known Activations