© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60576
    Prev
    Next
    INDEX
    Explanations

    hardcore explicit content

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

    The neuron activates on occurrences of the word “hardcore” across various contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ?
    -2.58
     Then
    -2.47
     condenado
    -2.11
    !
    -2.11
    </td>
    -2.08
    \
    -2.08
     ''
    -1.98
    噥
    -1.97
    \'
    -1.97
     plainte
    -1.88
    POSITIVE LOGITS
     hardcore
    2.39
    ！”
    2.33
    ization
    2.33
    actéristi
    2.31
    er
    2.27
    俅
    2.19
    ০
    2.13
    Ꮴ
    2.09
    IVENESS
    2.09
    ”,
    2.09
    Activations Density 0.002%

    No Known Activations