© 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. 26866
    Prev
    Next
    INDEX
    Explanations

    proper names that are followed by descriptions

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

    the presence of hexadecimal‐style chunks (long sequences of hex digits/letters) typically found in URLs or file‐name hashes.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     three
    -1.33
     two
    -1.21
     four
    -1.17
    فران
    -1.17
     before
    -1.11
     five
    -1.11
     fifteen
    -1.08
     several
    -1.06
     some
    -1.04
    رون
    -1.02
    POSITIVE LOGITS
    R
    1.03
    q
    1.00
    BT
    1.00
     amazing
    0.98
    у
    0.98
    uring
    0.97
    T
    0.97
    ou
    0.97
    AH
    0.96
    perative
    0.96
    Activations Density 0.001%

    No Known Activations