© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59911
    Prev
    Next
    INDEX
    Explanations

    Gibraltar or elongated shapes

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

    The neuron responds to unusually long words (tokens that span roughly eight to ten characters).

    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
    镦
    -2.55
    櫪
    -2.53
    鲠
    -2.52
    檮
    -2.36
    铼
    -2.28
    椟
    -2.27
    ᷆
    -2.25
    ⸰
    -2.14
    ætte
    -2.14
    lgari
    -2.13
    POSITIVE LOGITS
     \
    2.75
    It
    2.52
     animados
    2.30
     solchen
    2.22
     coloridos
    2.20
     complètes
    2.19
     elevados
    2.19
    One
    2.17
     größeren
    2.17
     pesados
    2.16
    Activations Density 0.003%

    No Known Activations