© 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. 228280
    Prev
    Next
    INDEX
    Explanations

    non-custodial parent

    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
     fallen
    0.48
     flawlessly
    0.47
    Anglo
    0.46
     lament
    0.46
    견
    0.45
     Anglo
    0.45
    0.45
    $&
    0.44
    кину
    0.44
    ¿
    0.44
    POSITIVE LOGITS
     조사
    0.52
    saw
    0.51
     मध
    0.49
     vindt
    0.49
    smoothing
    0.47
     Yusuf
    0.46
    umap
    0.46
    cmap
    0.46
    𝗵
    0.46
    ере
    0.46
    Activations Density 0.000%

    No Known Activations