© 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. 34-GEMMASCOPE-RES-131K
    7. 63746
    Prev
    Next
    INDEX
    Explanations

    sentence structure and grammar

    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
    ⁠
    -1.40
     envisaged
    -1.13
    fucking
    -1.08
     conclure
    -1.05
     FINDINGS
    -1.04
     plantes
    -1.04
     
    -1.03
    ̶
    -1.02
    breast
    -1.02
    📉
    -1.00
    POSITIVE LOGITS
     they
    1.30
     since
    1.16
     различни
    1.14
     students
    1.09
     because
    1.09
     their
    1.08
    كوم
    1.08
     используется
    1.08
     shows
    1.07
     τὸν
    1.06
    Activations Density 0.030%

    No Known Activations