© 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. 31-GEMMASCOPE-2-RES-16K
    7. 15627
    Prev
    Next
    INDEX
    Explanations

    text messages

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

    sexually suggestive or explicit

    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_16k_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
    },
    0.52
    chts
    0.52
    britann
    0.50
     журна
    0.49
    omos
    0.48
    cyte
    0.47
    hts
    0.47
    stas
    0.46
    alu
    0.46
    ],
    0.46
    POSITIVE LOGITS
    ವೀ
    0.49
     hawk
    0.49
    జయ
    0.49
     text
    0.48
     anarchist
    0.46
    Data
    0.45
    高峰
    0.45
     حقوق
    0.44
    ത്
    0.44
     jazdy
    0.44
    Activations Density 0.071%

    No Known Activations