© 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. 100912
    Prev
    Next
    INDEX
    Explanations

    shell command or interface

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

    the word "shell" in programming code contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     become
    -2.64
    鮰
    -2.56
     墊
    -2.36
     広場
    -2.30
     vitales
    -2.28
    搪
    -2.25
    v
    -2.23
    躂
    -2.14
    艽
    -2.14
     eſſ
    -2.14
    POSITIVE LOGITS
     isnt
    2.69
    経歴
    2.58
    実際に
    2.47
    what
    2.45
    }$
    2.38
    )$
    2.36
    л
    2.34
    徧
    2.31
    да
    2.31
    ).
    2.30
    Activations Density 0.005%

    No Known Activations