© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12263
    Prev
    Next
    INDEX
    Explanations

    pointers and memory addresses

    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
    _
    -1.08
     deliciosos
    -1.06
    цов
    -1.05
     Gemüse
    -1.03
     sieben
    -1.03
    身
    -1.02
    asus
    -1.02
     isolated
    -1.02
    ₇
    -1.01
     nazy
    -1.00
    POSITIVE LOGITS
     civili
    1.33
    というわけで
    1.26
    rées
    1.26
     suna
    1.20
     fata
    1.20
     sonde
    1.19
     cire
    1.17
     felic
    1.17
     santi
    1.16
    vité
    1.14
    Activations Density 0.005%

    No Known Activations