Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 9104
    Prev
    Next
    INDEX
    Explanations

    opening parenthesis in code

    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_34/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
     cinto
    -1.08
     piłkarz
    -1.07
     prachtig
    -1.05
    ابقة
    -1.05
     that
    -1.05
     fakta
    -1.04
    Также
    -1.03
     kabát
    -1.02
    Kaynakça
    -1.02
    tidumbre
    -1.02
    POSITIVE LOGITS
    )
    1.31
    !
    1.21
     !
    1.20
    e
    1.12
    .
    1.08
    y
    0.99
    ak
    0.96
    j
    0.94
     )
    0.93
    z
    0.92
    Activations Density 0.003%

    No Known Activations