© 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. 13278
    Prev
    Next
    INDEX
    Explanations

    not working or breaking

    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
    「
    -1.28
    <mask>
    -1.22
     tikai
    -1.11
    TWO
    -1.08
    のいい
    -1.08
     vegetación
    -1.07
    asjonen
    -1.07
    %;
    -1.05
    !\!\
    -1.05
     firestore
    -1.04
    POSITIVE LOGITS
     problems
    1.28
     issues
    1.16
     functionality
    1.11
    Expecting
    1.09
     error
    1.07
    훗
    1.05
    donate
    1.04
    ⍺
    1.01
     compatibility
    1.00
    訃
    1.00
    Activations Density 0.177%

    No Known Activations