© 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. 12256
    Prev
    Next
    INDEX
    Explanations

    Q:

    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
     There
    -1.66
     when
    -1.45
     and
    -1.44
     If
    -1.43
     When
    -1.41
     where
    -1.31
     latas
    -1.29
     instituto
    -1.29
     if
    -1.27
     there
    -1.27
    POSITIVE LOGITS
    必须要
    1.32
    蠓
    1.30
    al
    1.30
    ate
    1.23
     ´
    1.20
     "*
    1.20
     Dinas
    1.18
    ze
    1.17
    看了一眼
    1.16
    否认
    1.16
    Activations Density 0.041%

    No Known Activations