© 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. 22-GEMMASCOPE-RES-131K
    7. 26335
    Prev
    Next
    INDEX
    Explanations

    skin treatments

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

    Python import statements and module paths in code, particularly when accessing submodules with dot notation.

    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
    rainian
    -1.58
    bracelet
    -1.49
    anians
    -1.48
    が多く
    -1.48
    othes
    -1.44
     pertama
    -1.42
    giacca
    -1.42
    thodox
    -1.41
    も多く
    -1.38
    了几
    -1.37
    POSITIVE LOGITS
    M
    1.45
    C
    1.41
    utils
    1.34
    ₫
    1.31
    Cartney
    1.31
    N
    1.31
    Y
    1.30
    })->
    1.26
    んですよ
    1.24
    },[])
    1.22
    Activations Density 0.014%

    No Known Activations