© 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. 38779
    Prev
    Next
    INDEX
    Explanations

    Organic Teas, It is, Q:

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

    sequences of digits or hexadecimal characters, especially in rows of binary or encoded data.

    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_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
     этим
    -2.13
     этой
    -1.93
    ≍
    -1.82
    PÁG
    -1.73
     diesen
    -1.69
     competición
    -1.68
    ᾽
    -1.65
     эту
    -1.60
     they
    -1.60
     هذه
    -1.58
    POSITIVE LOGITS
     Però
    1.75
     scrittore
    1.72
     either
    1.69
     still
    1.65
    就可以了
    1.64
     drau
    1.58
     continuare
    1.55
     different
    1.55
     preferências
    1.55
     Nevertheless
    1.54
    Activations Density 0.007%

    No Known Activations