© 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. 58986
    Prev
    Next
    INDEX
    Explanations

    left hand side

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on spatial‐layout references—particularly “left hand side,” “right hand side,” or similar locational cues.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Úl
    -0.72
    packt
    -0.70
     Ј
    -0.69
     sqrt
    -0.68
     Lal
    -0.68
    aprend
    -0.68
    ismen
    -0.67
     Jé
    -0.67
    Én
    -0.67
    גרת
    -0.67
    POSITIVE LOGITS
     side
    2.88
     sides
    2.66
    side
    2.28
    Side
    2.13
     Side
    2.11
    sides
    1.96
     Sides
    1.72
    Sides
    1.57
     SIDE
    1.57
    sided
    1.52
    Activations Density 0.033%

    No Known Activations