© 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. 40057
    Prev
    Next
    INDEX
    Explanations

    new class() constructor calls

    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
     and
    -2.11
     an
    -1.30
    providedIn
    -1.27
     or
    -1.25
     first
    -1.21
     verbeteren
    -1.19
    に行ってきました
    -1.17
     verschillen
    -1.16
     fifteen
    -1.16
     During
    -1.15
    POSITIVE LOGITS
    は
    1.30
     famed
    1.27
     acclaimed
    1.27
     disgruntled
    1.24
     baseado
    1.24
    では
    1.20
     vastly
    1.20
    ですが
    1.19
     revamped
    1.19
    を使って
    1.18
    Activations Density 0.002%

    No Known Activations