© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11322
    Prev
    Next
    INDEX
    Explanations

    U.S. patent numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     after
    -1.30
     one
    -1.25
     when
    -1.19
     can
    -1.09
     since
    -1.06
     half
    -1.05
     how
    -1.04
    volts
    -1.03
     and
    -1.02
     or
    -1.02
    POSITIVE LOGITS
    因为
    1.28
    Utili
    1.20
    Assemblée
    1.18
    écriture
    1.17
    Ruj
    1.14
    Gambar
    1.13
    ༆
    1.12
     desear
    1.12
    Deus
    1.11
    élection
    1.11
    Activations Density 0.014%

    No Known Activations