© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 11519
    Prev
    Next
    INDEX
    Explanations

    applications and technical concepts

    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
     and
    -1.82
     it
    -1.45
     about
    -1.36
     not
    -1.31
     By
    -1.23
    N
    -1.21
     as
    -1.18
     The
    -1.14
     during
    -1.13
    NO
    -1.13
    POSITIVE LOGITS
    ⛦
    1.30
     Atención
    1.27
    𖧵
    1.22
     กร
    1.16
    ÍS
    1.15
    peño
    1.15
     belga
    1.14
    chrän
    1.13
    ouml
    1.13
     kär
    1.11
    Activations Density 0.143%

    No Known Activations