© 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. 26877
    Prev
    Next
    INDEX
    Explanations

    Nuclear matrix

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

    phrases indicating a shift in perspective or introducing a contrasting statement.

    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
    何も
    -1.06
    glUniform
    -0.85
    就可以
    -0.84
    같이
    -0.84
    .}(
    -0.83
    +};
    -0.81
    орты
    -0.81
    bac
    -0.81
     Jank
    -0.80
     dext
    -0.80
    POSITIVE LOGITS
     unavoidable
    1.30
     inevitable
    1.18
     inevit
    1.05
     modifikasi
    1.04
     reality
    1.01
     future
    0.98
     existing
    0.91
     will
    0.91
     tồn
    0.89
    emplares
    0.88
    Activations Density 0.044%

    No Known Activations