© 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. 34-GEMMASCOPE-RES-131K
    7. 60365
    Prev
    Next
    INDEX
    Explanations

    explicit sexual content

    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_34/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
     schafft
    -0.96
     तथा
    -0.86
     schaffen
    -0.82
     jspb
    -0.81
     północ
    -0.79
     verlangt
    -0.79
    ウェブ
    -0.78
     eignen
    -0.78
    敍
    -0.77
     lends
    -0.76
    POSITIVE LOGITS
     kollu
    0.86
     NAV
    0.85
    monument
    0.85
     nadru
    0.83
    ്യ
    0.83
    stoffen
    0.82
    },
    0.81
     zij
    0.79
     pomi
    0.78
     ass
    0.78
    Activations Density 0.040%

    No Known Activations