© 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. 22-GEMMASCOPE-RES-131K
    7. 34413
    Prev
    Next
    INDEX
    Explanations

    hobbies and interests

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

    The neuron fires on the post’s central subject–the key topic or domain‐specific noun that names what the text is about.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     “
    -1.29
    </em>
    -1.25
    “
    -1.20
     „
    -1.05
    ");
    -1.03
    LEFT
    -1.00
     wees
    -1.00
     
    -0.99
     the
    -0.98
    ів
    -0.98
    POSITIVE LOGITS
     různ
    1.27
     hlavně
    1.26
     ativar
    1.22
     melhorar
    1.20
     acompanhar
    1.19
     자신의
    1.18
     různých
    1.16
     Tamanho
    1.13
    Zdra
    1.13
     opět
    1.13
    Activations Density 0.078%

    No Known Activations