© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66539
    Prev
    Next
    INDEX
    Explanations

    starting and backup positions

    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
    andescent
    -1.17
     distintos
    -1.16
     volverá
    -1.13
     rencont
    -1.05
    StreetMap
    -1.05
    也算是
    -1.05
    違った
    -1.05
     ۱۰
    -1.04
     individuell
    -1.03
     combate
    -1.02
    POSITIVE LOGITS
     their
    1.10
    parently
    1.07
     Both
    1.07
     Наталья
    1.05
    ditionally
    1.04
    ساس
    1.00
     eingeladen
    0.99
    vail
    0.98
     Роман
    0.98
     both
    0.96
    Activations Density 0.025%

    No Known Activations