© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8647
    Prev
    Next
    INDEX
    Explanations

    contractions like 's, 'd, 't

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

    K-Means

    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_53_width_65k_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
    perturbative
    0.38
    }${
    0.38
    ][%
    0.37
    :%
    0.37
    টিক
    0.36
    ][:
    0.36
    बॉलीवुड
    0.36
    }.${
    0.36
     asegur
    0.35
    湡
    0.35
    POSITIVE LOGITS
    __
    0.46
     Webster
    0.45
     Dalton
    0.42
     Kramer
    0.41
     Gideon
    0.40
     __
    0.39
     tumbler
    0.39
     tandem
    0.39
     ক্রোধ
    0.38
    шёл
    0.38
    Activations Density 0.001%

    No Known Activations