© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 65543
    Prev
    Next
    INDEX
    Explanations

    converting to string

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

    The neuron fires on calls that convert values to strings (e.g. “str(…)” or “String.valueOf(…)”).

    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
     but
    -1.31
     ۱۴
    -1.21
     joão
    -1.20
     such
    -1.19
    哧
    -1.16
     against
    -1.16
    manuelle
    -1.15
     Such
    -1.15
     infância
    -1.12
     خواهد
    -1.10
    POSITIVE LOGITS
     of
    2.00
    ғы
    1.34
    re
    1.34
    p
    1.28
    er
    1.27
     impresionantes
    1.26
     espectaculares
    1.23
    o
    1.23
     naszego
    1.17
    or
    1.15
    Activations Density 0.001%

    No Known Activations