© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39029
    Prev
    Next
    INDEX
    Explanations

    Pathfinder game system rules

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

    The neuron fires on edition/version identifiers—numeric or alphanumeric version labels (e.g. “3.x,” “4E,” etc.).

    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
     akumulator
    -1.50
     during
    -1.47
     when
    -1.39
     Sabtu
    -1.35
     after
    -1.33
     Selasa
    -1.27
     other
    -1.27
    ּוֹ
    -1.27
    ıla
    -1.26
     Internasional
    -1.26
    POSITIVE LOGITS
    匾
    1.55
     掃除
    1.51
     passagers
    1.41
    蝼
    1.39
    рѣ
    1.39
     prêtres
    1.39
     atque
    1.37
    laması
    1.37
    ugier
    1.34
     chré
    1.34
    Activations Density 0.041%

    No Known Activations