© 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. 22-GEMMASCOPE-RES-131K
    7. 75360
    Prev
    Next
    INDEX
    Explanations

    Q followed by colon

    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
    ּוֹ
    -1.16
    ategori
    -1.09
     σα
    -1.07
    ִּ
    -1.06
    pekte
    -0.99
    rtp
    -0.98
    guint
    -0.96
    structing
    -0.95
    xff
    -0.94
     focus
    -0.90
    POSITIVE LOGITS
    㩒
    1.07
     Avg
    1.00
    灕
    0.99
     qualcuno
    0.93
    bestimmungen
    0.93
     nuk
    0.93
     cittad
    0.93
     procurer
    0.93
     popolare
    0.92
     modificare
    0.91
    Activations Density 0.000%

    No Known Activations