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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 90276
    Prev
    Next
    INDEX
    Explanations

    specific groups or contexts

    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_10/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
    Recommended
    -1.18
    ???:
    -1.15
    回到了
    -1.14
    Lett
    -1.11
    ilets
    -1.09
    هر
    -1.09
     moule
    -1.08
    return
    -1.08
    assertThrows
    -1.08
     failings
    -1.07
    POSITIVE LOGITS
     your
    2.09
     also
    1.61
     both
    1.55
     such
    1.45
     those
    1.36
     también
    1.28
     yourself
    1.25
     these
    1.18
     June
    1.16
     each
    1.12
    Activations Density 0.235%

    No Known Activations