© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72419
    Prev
    Next
    INDEX
    Explanations

    childlike immaturity and youth

    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
     neceſſ
    -1.49
    龶
    -1.45
     &#
    -1.36
     londres
    -1.36
    quien
    -1.31
     ſhe
    -1.29
     särskilt
    -1.28
    歺
    -1.28
     stöd
    -1.27
     alſo
    -1.26
    POSITIVE LOGITS
     besseren
    1.51
    𝕱
    1.49
     üblichen
    1.47
    ፳
    1.47
     immature
    1.46
     wiederhol
    1.44
     einfacher
    1.41
    1
    1.40
     Vielzahl
    1.39
     meisten
    1.38
    Activations Density 0.018%

    No Known Activations