© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 43020
    Prev
    Next
    INDEX
    Explanations

    in which

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

    The neuron fires on mentions of record‐label credits, e.g. “for Ayler Records,”.

    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
     into
    -1.50
     one
    -1.30
     voulait
    -1.19
     have
    -1.16
     aurait
    -1.16
     its
    -1.11
     from
    -1.11
     only
    -1.08
     further
    -1.06
    '
    -1.05
    POSITIVE LOGITS
     genau
    1.21
     Перейти
    1.20
     عندما
    1.18
    sekten
    1.18
    xff
    1.15
    }$,
    1.15
     them
    1.14
     これ
    1.13
     использования
    1.11
     dní
    1.11
    Activations Density 0.107%

    No Known Activations