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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39888
    Prev
    Next
    INDEX
    Explanations

    code headers and identifiers

    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
    textEdit
    -1.52
    jelaskan
    -1.38
     جذاب
    -1.35
     reisen
    -1.35
    utveck
    -1.31
     Gesund
    -1.28
    るので
    -1.27
     our
    -1.27
     tyn
    -1.27
     baada
    -1.26
    POSITIVE LOGITS
     but
    1.49
     gehör
    1.45
    pexpr
    1.41
    InstrumentedTest
    1.39
    }}
    1.35
                
    1.34
    ১
    1.34
     seines
    1.33
    rceil
    1.32
     njego
    1.31
    Activations Density 0.016%

    No Known Activations