© 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. 31663
    Prev
    Next
    INDEX
    Explanations

    direction: left

    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
     сверху
    -1.09
    top
    -1.04
    offsetTop
    -0.95
     top
    -0.92
     верхней
    -0.91
    OnTop
    -0.89
    getTop
    -0.86
     podkre
    -0.85
    IsOptional
    -0.83
    верху
    -0.83
    POSITIVE LOGITS
     left
    1.84
    left
    1.23
     right
    1.23
     Left
    1.20
    左右
    1.18
    Left
    1.01
     izquierda
    0.98
    左
    0.94
    LEFT
    0.92
     LEFT
    0.92
    Activations Density 0.016%

    No Known Activations