© 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. 128492
    Prev
    Next
    INDEX
    Explanations

    programming exceptions and keywords

    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
     was
    -2.61
     called
    -2.52
     termed
    -2.38
     followed
    -2.17
     told
    -2.13
     believed
    -2.11
     reached
    -2.09
     caught
    -2.06
     sent
    -2.05
     said
    -2.03
    POSITIVE LOGITS
    2.19
    _
    2.19
    </strong>
    2.08
    with
    2.00
    <bos>
    1.92
     membersihkan
    1.91
    the
    1.89
    琤
    1.86
     összefoglaló
    1.86
     berkomunikasi
    1.85
    Activations Density 0.000%
    No Known Activations