© 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. 84456
    Prev
    Next
    INDEX
    Explanations

    `super` followed by init/setup methods

    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
     camuf
    -1.15
     jednocześnie
    -1.13
    \\
    -1.11
     veröffentlich
    -1.10
     brachte
    -1.09
    ABOR
    -1.09
     ""
    -1.08
     arries
    -1.06
     ladr
    -1.06
     refugi
    -1.05
    POSITIVE LOGITS
     will
    1.45
    ,
    1.23
    </strong>
    1.17
    </b>
    1.16
    </i>
    1.15
     Sorgen
    1.00
     in
    0.99
    7
    0.97
     denomin
    0.97
    3
    0.96
    Activations Density 0.001%

    No Known Activations