© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68492
    Prev
    Next
    INDEX
    Explanations

    closing punctuation followed by text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Otras
    -0.83
     város
    -0.82
    Estos
    -0.82
     MAKES
    -0.79
    稳
    -0.79
     BUSINESS
    -0.79
    CONTENIDO
    -0.78
     Otros
    -0.78
     Reparatur
    -0.77
     nullable
    -0.77
    POSITIVE LOGITS
    Regards
    1.08
     only
    0.98
     again
    0.92
    Repos
    0.90
    tamment
    0.90
    ώ
    0.87
     őket
    0.84
    字节
    0.84
     ibid
    0.84
     Regards
    0.84
    Activations Density 0.009%

    No Known Activations