© 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. 10-GEMMASCOPE-RES-131K
    7. 129651
    Prev
    Next
    INDEX
    Explanations

    earth's environment and history

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

    the word "Earth" when referring to the planet Earth.

    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
    ⩴
    -2.75
    ፨
    -2.50
    銫
    -2.42
    Ꮏ
    -2.41
    ֎
    -2.38
    になるので
    -2.27
    でしたね
    -2.27
    ឵
    -2.25
    焢
    -2.13
     diputados
    -2.09
    POSITIVE LOGITS
    {
    3.41
    "
    3.39
     \
    2.86
     you
    2.48
    ON
    2.39
    месте
    2.31
    ly
    2.30
    (
    2.27
    ts
    2.23
    новь
    2.22
    Activations Density 0.006%

    No Known Activations