© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66832
    Prev
    Next
    INDEX
    Explanations

    public class, intramolecular, Q:

    np_acts-logits-general · gemini-2.5-flash-lite

    code formatting and indentation patterns in programming contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    使う
    -1.03
     decisi
    -0.96
    之後
    -0.93
     discer
    -0.91
     kontinuier
    -0.91
     fiasco
    -0.89
    AGUE
    -0.87
    any
    -0.85
     selva
    -0.82
     erstaun
    -0.82
    POSITIVE LOGITS
    assemblée
    1.09
    Assemblée
    1.02
    botines
    1.01
    LEGGI
    1.00
    requestCode
    0.99
    bB
    0.99
    》：
    0.98
    pii
    0.96
    трим
    0.95
     sneaking
    0.95
    Activations Density 0.000%

    No Known Activations