© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78395
    Prev
    Next
    INDEX
    Explanations

    subscribe to content or services

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

    The neuron detects occurrences of “subscribe” or “subscription” prompts and related subscription-calling phrases.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    跟你
    -1.15
    绔
    -1.08
     クリップ
    -1.08
     uſe
    -1.06
    颪
    -1.04
    奁
    -1.03
     sporadic
    -1.02
     secluded
    -1.02
     protože
    -0.99
    ライズ
    -0.98
    POSITIVE LOGITS
     FOR
    1.17
    ↵
    1.10
    \
    1.07
    𝓻
    1.06
     WAY
    1.02
     During
    1.02
     Despite
    0.98
    ).
    0.98
    мять
    0.97
    ?
    0.97
    Activations Density 0.010%

    No Known Activations