© 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. 19228
    Prev
    Next
    INDEX
    Explanations

    our [descriptor/possessive]

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

    my or our followed by a descriptor

    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
    ərb
    0.47
    ạc
    0.47
    구
    0.46
    ⓓ
    0.46
    ác
    0.45
    ăţ
    0.45
    ሰ
    0.45
    쿠
    0.44
     width
    0.44
     cherche
    0.44
    POSITIVE LOGITS
     Turned
    0.47
     »,
    0.43
     रीड
    0.42
     Ganz
    0.42
    dings
    0.41
     Championship
    0.40
    usions
    0.40
     Editor
    0.40
     Complet
    0.40
     Championships
    0.40
    Activations Density 0.000%

    No Known Activations