© 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. 10-GEMMASCOPE-RES-131K
    7. 41550
    Prev
    Next
    INDEX
    Explanations

    years and years

    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_10/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
    -2.13
     but
    -1.84
    when
    -1.78
    tır
    -1.56
    ｋ
    -1.45
     tetapi
    -1.43
     after
    -1.42
    derdag
    -1.40
     když
    -1.39
     ``
    -1.36
    POSITIVE LOGITS
     your
    1.63
     our
    1.50
     italianos
    1.48
    petual
    1.43
    CHREIB
    1.41
    </h5>
    1.38
    はずです
    1.38
    れました
    1.36
     limpa
    1.35
    Elő
    1.35
    Activations Density 0.042%

    No Known Activations