© 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. 129523
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on occurrences of “hash”-related terms (e.g. hashCode, hashable, hash).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    Q: questions and code

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    -1.52
    </h3>
    -1.34
     einer
    -1.23
     学院
    -1.20
     mastery
    -1.16
     картина
    -1.16
     bVar
    -1.15
    噥
    -1.15
     usual
    -1.14
     immersed
    -1.13
    POSITIVE LOGITS
     drücken
    1.33
    ントン
    1.27
     keberadaan
    1.18
    裡的
    1.17
     senhor
    1.17
     Oggi
    1.13
    olastic
    1.12
    ឵
    1.12
    ably
    1.11
     précisément
    1.11
    Activations Density 0.001%

    No Known Activations