© 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. 40579
    Prev
    Next
    INDEX
    Explanations

    scavenger, scavenging, scavenged

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

    words related to scavenging or gathering, particularly the word "scavenger" and its variations.

    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
    ”;
    -2.66
    The
    -2.56
    ?”
    -2.38
    猻
    -2.22
    揷
    -2.19
     вещей
    -2.17
    ・・・・
    -2.16
    泐
    -2.14
     剤
    -2.13
    桖
    -2.11
    POSITIVE LOGITS
    ?
    2.75
    <bos>
    2.34
     ("
    2.22
    沨
    2.22
    来ました
    2.06
    '
    2.06
    \|^{
    2.05
     "
    2.05
    ierung
    1.96
    "'
    1.91
    Activations Density 0.004%

    No Known Activations