© 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. 158048
    Prev
    Next
    INDEX
    Explanations

    Westport City mommy drawings

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

    confusion in bed or financial declines

    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
    тих
    0.53
    ريخ
    0.48
    تي
    0.48
    лү
    0.47
     κόσ
    0.47
     gême
    0.46
    杪
    0.46
    тился
    0.46
    тный
    0.45
     ナイス
    0.45
    POSITIVE LOGITS
    ],
    0.50
     recombination
    0.49
    "])
    0.46
    ant
    0.45
     oll
    0.43
    adata
    0.43
    "),
    0.42
    %),
    0.42
    ),
    0.41
     rehearing
    0.40
    Activations Density 0.000%

    No Known Activations