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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 66404
    Prev
    Next
    INDEX
    Explanations

    orientation and rotation

    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
     garantías
    -0.82
    illots
    -0.77
     accordé
    -0.77
     Picks
    -0.75
     menak
    -0.74
     گونه
    -0.73
    ounding
    -0.73
    -=
    -0.71
    gorod
    -0.70
     größeren
    -0.70
    POSITIVE LOGITS
    ឹ
    0.92
     supported
    0.85
    Rotate
    0.85
    reur
    0.84
    旋转
    0.81
     accelerometer
    0.81
    Supported
    0.81
     Device
    0.79
    DEVICE
    0.79
    Device
    0.79
    Activations Density 0.015%

    No Known Activations