© 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. 39161
    Prev
    Next
    INDEX
    Explanations

    Acoustic neuroma, Product Description, Photosynthesis

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

    numeric identifiers or values in technical documentation or code.

    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
    papar
    -1.20
     Pièces
    -1.12
    bunga
    -1.09
     dança
    -1.09
    piram
    -1.08
    stoy
    -1.08
    guigu
    -1.06
    kumpulan
    -1.06
     solides
    -1.05
    gilet
    -1.05
    POSITIVE LOGITS
    B
    1.09
     Stadia
    1.07
    at
    1.05
    u
    1.04
     yakni
    1.04
    E
    1.02
    j
    1.02
    aj
    1.01
    D
    1.01
     ノース
    1.00
    Activations Density 0.001%

    No Known Activations