© 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. 3078
    Prev
    Next
    INDEX
    Explanations

    propose and present methods

    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
     เปิด
    -1.00
    řej
    -0.97
    لباس
    -0.92
    Trump
    -0.89
    脚注の使い方
    -0.88
     vielleicht
    -0.88
     hipó
    -0.87
     nakalista
    -0.87
    سین
    -0.86
     않습니다
    -0.86
    POSITIVE LOGITS
     proposed
    1.41
     Proposed
    1.31
     propose
    1.13
    Proposed
    1.06
    Faults
    1.03
     PROPOSED
    0.98
    PROPOSED
    0.98
     wireless
    0.90
     Raspberry
    0.89
    proposed
    0.88
    Activations Density 0.076%

    No Known Activations