© 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. 37827
    Prev
    Next
    INDEX
    Explanations

    left and right directions

    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
    ಱ
    -1.01
     higien
    -0.95
    懨
    -0.91
    嫆
    -0.91
     Psico
    -0.88
    XIM
    -0.88
    cenary
    -0.86
     yp
    -0.85
     pior
    -0.85
     ônibus
    -0.85
    POSITIVE LOGITS
     right
    2.05
     left
    1.73
     immediate
    1.63
     far
    1.52
    immediate
    1.27
     extreme
    1.23
     droite
    1.15
     immédi
    1.09
    Immediate
    1.06
    far
    1.05
    Activations Density 0.026%

    No Known Activations