© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 91076
    Prev
    Next
    INDEX
    Explanations

    flex direction

    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
     frases
    -0.82
    fated
    -0.81
     pasan
    -0.79
    ведений
    -0.79
     издание
    -0.78
     Fe
    -0.76
     id
    -0.76
     prime
    -0.73
     cô
    -0.73
     кух
    -0.73
    POSITIVE LOGITS
     direction
    1.23
    direction
    1.09
    Direction
    1.05
     basis
    0.98
    Diret
    0.93
     Ugandan
    0.86
    وقد
    0.85
    Shrink
    0.84
     shrinking
    0.84
    Direccion
    0.83
    Activations Density 0.002%

    No Known Activations